Podcasts about Econometrica

In this episode, we delve into the critical work of developing and implementing models designed to improve collaborative learning networks and disseminate best practices. From rapid cycle evaluations to leveraging cutting-edge technology, these efforts aim to deliver actionable insights and transformative outcomes.Key Highlights:Requirements in Focus:Developing and implementing innovative models.Conducting rapid cycle evaluations to optimize programs and participant outcomes.Building robust collaborative networks and technology to support widespread adoption.Incumbent Insights: Learn about the companies currently positioned for this work, including Arbor Research Collaborative for Health, Econometrica, Inc., and Westat, Inc., and explore why task orders have yet to be issued under this contract.Gain unique perspectives on the challenges and opportunities in rapid evaluation and reporting, and how these practices are shaping the future of program development.Listen now to uncover strategies for maximizing innovation and driving impact through rapid cycle analysis.Contact ProposalHelper at sales@proposalhelper.com to find similar opportunities and help you build a realistic and winning pipeline.

Welcome to Nerd Alert, a series of special episodes bridging the gap between marketing academia and practitioners. We're breaking down highly involved, complex research into plain language and takeaways any marketer can use.In this episode, Elena and Rob explore a large-scale eBay experiment that challenges common assumptions about paid search advertising effectiveness. They discover that brand-keyword ads often reach customers who would have found the site anyway, and even non-branded keywords generate negative ROI.Topics covered:[01:00] "Consumer Heterogeneity and Paid Search Effectiveness: A Large Scale Field Experiment"[02:35] Why marketers avoid clicking paid search ads[03:45] eBay's massive experiment design[06:00] The surprising impact on frequent buyers[07:10] Shocking ROI results[08:30] What this means for established brands  To learn more, visit marketingarchitects.com/podcast or subscribe to our newsletter at marketingarchitects.com/newsletter. Resources: Blake, T., Nosko, C., & Tadelis, S. (2014). Consumer Heterogeneity and Paid Search Effectiveness: A Large-Scale Field Experiment. Econometrica.  Get more research-backed marketing strategies by subscribing to The Marketing Architects on Apple Podcasts, Spotify, or wherever you listen to podcasts. 

To join the village fundraiser, help send life changing cash and support research like this, visit https://www.givedirectly.org/macro/ Interview with Oxford prof Dennis Egger about his Econometrica paper: General Equilibrium Effects of Cash Transfers: Experimental Evidence From Kenya, with  Johannes Haushofer, Edward Miguel, Paul Niehaus, Michael Walker

Conceptual papers that offer new theories are hard to write and even harder to publish. You do not have empirical data to back up your arguments, which makes the papers easy to reject in the review cycle. We are also typically not well trained in theorizing, and there isn't even a clear process to theorizing we could learn or follow. Does that mean that we shouldn't even try to write theory papers? We ponder these questions, figure out what is so hard in writing conceptual papers – and share a few tricks that might help if you still wanted to write such a paper.  References Berente, N., Gu, B., Recker, J., & Santhanam, R. (2021). Managing Artificial Intelligence. MIS Quarterly, 45(3), 1433-1450. Glaser, B. G., & Strauss, A. L. (1967). The Discovery of Grounded Theory: Strategies for Qualitative Research. Aldine Publishing Company. Watson, R. T., Boudreau, M.-C., & Chen, A. J. (2010). Information Systems and Environmentally Sustainable Development:  Energy Informatics and New Directions for the IS Community. MIS Quarterly, 34(1), 23-38. Lee, A. S., & Baskerville, R. (2003). Generalizing Generalizability in Information Systems Research. Information Systems Research, 14(3), 221-243. Tsang, E. W. K., & Williams, J. N. (2012). Generalization and Induction: Misconceptions, Clarifications, and a Classification of Induction. MIS Quarterly, 36(3), 729-748. Yoo, Y., Henfridsson, O., & Lyytinen, K. (2010). The New Organizing Logic of Digital Innovation: An Agenda for Information Systems Research. Information Systems Research, 21(4), 724-735. Yoo, Y. (2010). Computing in Everyday Life: A Call for Research on Experiential Computing. MIS Quarterly, 34(2), 213-231. Merleau-Ponty, M. (1962). Phenomenology of Perception Routledge. Baldwin, C. Y., & Clark, K. B. (2000). Design Rules, Volume 1: The Power of Modularity. MIT Press. Weick, K. E. (1989). Theory Construction as Disciplined Imagination. Academy of Management Review, 14(4), 516-531. Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004). Design Science in Information Systems Research. MIS Quarterly, 28(1), 75-105. Sætre, A. S., & van de Ven, A. H. (2021). Generating Theory by Abduction. Academy of Management Review, 46(4), 684-701. Kahneman, D., & Tversky, A. (1979). Prospect Theory: An Analysis of Decision under Risk. Econometrica, 47(2), 263-291. Farjoun, M. (2010). Beyond Dualism: Stability and Change As a Duality. Academy of Management Review, 35(2), 202-225. Recker, J., & Green, P. (2019). How do Individuals Interpret Multiple Conceptual Models? A Theory of Combined Ontological Completeness and Overlap. Journal of the Association for Information Systems, 20(8), 1210-1241. Jabbari, M., Recker, J., Green, P., & Werder, K. (2022). How Do Individuals Understand Multiple Conceptual Modeling Scripts? Journal of the Association for Information Systems, 23(4), 1037-1070. Cornelissen, J. P. (2017). Editor's Comments: Developing Propositions, a Process Model, or a Typology? Addressing the Challenges of Writing Theory Without a Boilerplate. Academy of Management Review, 42(1), 1-9. Recker, J., Lukyanenko, R., Jabbari, M., Samuel, B. M., & Castellanos, A. (2021). From Representation to Mediation: A New Agenda for Conceptual Modeling Research in a Digital World. MIS Quarterly, 45(1), 269-300. Haerem, T., Pentland, B. T., & Miller, K. (2015). Task Complexity: Extending a Core Concept. Academy of Management Review, 40(3), 446-460. Kallinikos, J., Aaltonen, A., & Marton, A. (2013). The Ambivalent Ontology of Digital Artifacts. MIS Quarterly, 37(2), 357-370. Ho, S. Y., Recker, J., Tan, C.-W., Vance, A., & Zhang, H. (2023). MISQ Special Issue on Registered Reports. MIS Quarterly, . Simon, H. A. (1990). Bounded Rationality. In J. Eatwell, M. Milgate, & P. Newman (Eds.), Utility and Probability (pp. 15-18). Palgrave Macmillan. James, W. (1890). The Principles of Psychology. Henry Holt and Company. Watson, H. J. (2009). Tutorial: Business Intelligence - Past, Present, and Future. Communications of the Association for Information Systems, 25(39), 487-510.  Baird, A., & Maruping, L. M. (2021). The Next Generation of Research on IS Use: A Theoretical Framework of Delegation to and from Agentic IS Artifacts. MIS Quarterly, 45(1), 315-341.

Did you know that when you spend time on an online platform, you could be experiencing between six to eight different experimental treatments that stem from several hundred A/B tests that run concurrently? That's how common digital experimentation is today. And while this may be acceptable in industry, large-scale digital experimentation poses some substantial challenges for researchers wanting to evaluate theories and disconfirm hypotheses through randomized controlled trials done on digital platforms. Thankfully, the brilliant has a new paper forthcoming that illuminates the orthogonal testing plane problem and offers some guidelines for sidestepping the issue. So if experiments are your thing, you really need to listen to what is really going on out there. References Abbasi, A., Somanchi, S., & Kelley, K. (2024). The Critical Challenge of using Large-scale Digital Experiment Platforms for Scientific Discovery. MIS Quarterly, . Miranda, S. M., Berente, N., Seidel, S., Safadi, H., & Burton-Jones, A. (2022). Computationally Intensive Theory Construction: A Primer for Authors and Reviewers. MIS Quarterly, 46(2), i-xvi. Karahanna, E., Benbasat, I., Bapna, R., & Rai, A. (2018). Editor's Comments: Opportunities and Challenges for Different Types of Online Experiments. MIS Quarterly, 42(4), iii-x. Kohavi, R., & Thomke, S. (2017). The Surprising Power of Online Experiments. Harvard Business Review, 95(5), 74-82. Fisher, R. A. (1935). The Design of Experiments. Oliver and Boyd. Pienta, D., Vishwamitra, N., Somanchi, S., Berente, N., & Thatcher, J. B. (2024). Do Crowds Validate False Data? Systematic Distortion and Affective Polarization. MIS Quarterly, . Bapna, R., Goes, P. B., Gupta, A., & Jin, Y. (2004). User Heterogeneity and Its Impact on Electronic Auction Market Design: An Empirical Exploration. MIS Quarterly, 28(1), 21-43. Somanchi, S., Abbasi, A., Kelley, K., Dobolyi, D., & Yuan, T. T. (2023). Examining User Heterogeneity in Digital Experiments. ACM Transactions on Information Systems, 41(4), 1-34. Mertens, W., & Recker, J. (2020). New Guidelines for Null Hypothesis Significance Testing in Hypothetico-Deductive IS Research. Journal of the Association for Information Systems, 21(4), 1072-1102. GRADE Working Group. (2004). Grading Quality of Evidence and Strength of Recommendations. British Medical Journal, 328(7454), 1490-1494. Abbasi, A., Parsons, J., Pant, G., Liu Sheng, O. R., & Sarker, S. (2024). Pathways for Design Research on Artificial Intelligence. Information Systems Research, 35(2), 441-459. Abbasi, A., Chiang, R. H. L., & Xu, J. (2023). Data Science for Social Good. Journal of the Association for Information Systems, 24(6), 1439-1458. Babar, Y., Mahdavi Adeli, A., & Burtch, G. (2023). The Effects of Online Social Identity Signals on Retailer Demand. Management Science, 69(12), 7335-7346. Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004). Design Science in Information Systems Research. MIS Quarterly, 28(1), 75-105. Kahneman, D., & Tversky, A. (1979). Prospect Theory: An Analysis of Decision under Risk. Econometrica, 47(2), 263-291. Benbasat, I., & Zmud, R. W. (2003). The Identity Crisis Within The IS Discipline: Defining and Communicating The Discipline's Core Properties. MIS Quarterly, 27(2), 183-194. Gregor, S., & Hevner, A. R. (2013). Positioning and Presenting Design Science Research for Maximum Impact. MIS Quarterly, 37(2), 337-355. Rai, A. (2017). Editor's Comments: Avoiding Type III Errors: Formulating IS Research Problems that Matter. MIS Quarterly, 41(2), iii-vii. Burton-Jones, A. (2023). Editor's Comments: Producing Significant Research. MIS Quarterly, 47(1), i-xv.  Abbasi, A., Dillon, R., Rao, H. R., & Liu Sheng, O. R. (2024). Preparedness and Response in the Century of Disasters: Overview of Information Systems Research Frontiers. Information Systems Research, 35(2), 460-468.

with Dan Boneh @tim_roughgarden @smc90In this special 50th episode of the web3 with a16z podcast, we discuss how work in the blockchains/ crypto space has led to advances in several important technologies — which can be (and are being) used by many other industries beyond crypto.Tim Roughgarden (a16z crypto Head of Research and professor at Columbia University) and Dan Boneh (a16z crypto Senior Research Advisor and professor at Stanford University) discuss these advances in conversation with Sonal Chokshi. Topics covered include automated market makers; credible auctions, collusion, and mechanism design not possible before; as well as zero knowledge; trusted execution environments (TEEs) and fully homomorphic encryption (FHE); and much more. We also discuss the recurring theme of how web3 provides a laboratory not only for experiments in governance, but for macroeconomics and more. The two also offer many useful explanations for anyone new to these technologies or seeking to understand why they matter in the big picture. It's an innovation story we've seen over and over again, from the space program to other massive invention efforts: Technologies developed for one purpose often lead to benefits for humanity overall.Pieces mentioned in this episode and other resources:On some results  and challenges in cryptoeconomics  -- Tim Roughgarden, CESC 20228 reasons why blockchain mechanism design is hard -- Tim Roughgarden, a16zcrypto.com, 2024The computer in the sky (short version) -- Tim Roughgarden,  2024Zero knowledge canon -- with Justin Thaler's annotated bibliography, a16zcrypto,com 2022Using zero-knowledge proofs to fight disinformation -- Trisha Datta and Dan Boneh, IACR 2023VerITAS: Verifying Image Transformations at Scale -- Trisha Datta, Binyi Chen, Dan Boneh, 2024Achieving crypto privacy and regulatory compliance [+pdf of full paper]-- Joseph Burleson, Michele Korver, Dan Boneh, 2022Credible auctions: A trilemma -- Mohammad Akbarpour, Shengwu Li, Econometrica, 2020Auction design for web3 [episode 3 of this podcast] -- Scott Duke Kominers, Tim Roughgarden, Sonal Chokshi, 2022Building Cicada: Private on-chain voting using time-lock puzzles -- Michael Zhu, 2023Transaction fee mechanism design for the Ethereum blockchain: An economic analysis of EIP-1559 -- Tim Roughgarden, 2020Collusion-resilience in transaction fee mechanism design -- Hao Chung, Tim Roughgarden, Elaine Shi, 2024Transaction fee mechanism design in a Post-MEV world -- Maryam Bahrani, Pranav Garimidi,Tim Roughgarden, 2024Notes on Proposer-Builder Separation (PBS) -- Barnabé Monnot, 2022Complexity-approximation trade-offs in exchange mechanisms: AMMs vs. LOBs -- Jason Milionis, Ciamac Moallemi, Tim Roughgarden, 2023Trusted execution environments (TEEs) for blockchain applications -- Ari Juels, a16zcrypto.com, 2023 As a reminder, none of the following is investment, business, legal, or tax advice; please see a16z.com/disclosures for more important information including a link to a list of our investments.  

« If you cannot control your emotions, you cannot control your money. » - Warren Buffet La finance comportementale apparaît vraisemblablement dans l'histoire sous sa forme officielle il y a environ un peu plus d'une quarantaine d'années. Les auteurs Daniel Kahneman et Amos Tversky publient en 1979 dans la revue Econometrica un article intitulé Prospect Theory : An Analysis Of Decision Under Risk. Cet article soulevait des critiques face aux modèles reconnus à l'époque et il avançait que des mécanismes subjectifs pouvaient prendre une place significative dans le processus de décision en contexte financier, voire occasionnellement plus grande que celle de la raison.https://www.daytradercanada.com/billet-boursier/la-finance-comportementalecest-quoi-au-juste/Site web: https://daytradercanada.com/Nous joindre: https://daytradercanada.com/nous-joindre/Facebook: https://www.facebook.com/daytradercanadaYoutube: https://www.youtube.com/@DayTraderCanadaLinkedIn: https://www.linkedin.com/company/day-trader-canada/

Not everyone realizes that the modern financial system has enabled us to end historical practices such as indentured servitude and apprenticeship.  This episode uncovers how financial systems tackled market failures and transaction costs, drawing on insights from Jeffrey Hodgson's "The Wealth of a Nation: Institutional Foundations of English Capitalism." We'll explore the evolution of borrowing against future earnings and how modern financial institutions have streamlined processes that once resembled slavery, fostering the growth of capitalism.We'll then shift gears to examine Glenn Lowry's groundbreaking views on educational investment, discussed in his book "Late Admissions" and echoed in his 1981 Econometrica paper. Lowry's exploration of intergenerational transfers and parental investments in education reveals significant inefficiencies in the current system, drawing parallels with Michael Hudson's analysis of financial markets. The conversation sheds light on the untapped potential of underprivileged children and the need for better financial instruments to optimize educational funding.Geoffrey Hodgson. The Wealth of a Nation: Institutional Foundations of English Capitalism. Princeton University Press.  https://press.princeton.edu/books/hardcover/9780691247014/the-wealth-of-a-nation Glenn Loury, (1981). Intergenerational Transfers and the Distribution of Earnings. Econometrica, 49(4), 843–867. https://doi.org/10.2307/1912506What Causes Capitalism? STEPHEN DAVIES. REASON.   https://reason.com/?p=8285302Nick Gillespie Interviews Glenn Loury, REASON, https://reason.com/podcast/2024/06/12/glenn-loury-tales-of-sex-drugs-and-capitalism/If you have questions or comments, or want to suggest a future topic, email the show at taitc.email@gmail.com ! You can follow Mike Munger on Twitter at @mungowitz

Se acompanha o IN-Pertinente, saberá certamente que a economia se divide em duas grandes áreas de estudo: a microeconomia e a macroeconomia. Mas será que a segunda vive sem a primeira?Granularidade, networks (económicas) e as narrativas na economia são três mecanismos da chamada Nova Economia, e a conversa entre Mariana Alvim e José Alberto Ferreira vai explorá-los em detalhe, neste episódio. A dupla traz à ‘antena' não apenas a explicação teórica destes conceitos da macroeconomia, mas também exemplos reais: a chuva na Eslovénia que afetou a Autoeuropa em Portugal, a crise da indústria automóvel nos Estados Unidos que fez com que marcas concorrentes se protegessem umas às outras, os efeitos do ‘fenómeno Taylor Swift' ou como um desenho num guardanapo e uma história bem contada desencadearam cortes de impostos na América.Um único evento ou um único agente (uma empresa ou uma pessoa) – ou até uma simples história que se torna viral – pode ter grandes consequências macroeconómicas, chegando mesmo a ser capaz de originar uma recessão ou alavancar o crescimento da economia.REFERÊNCIAS E LINKS ÚTEISLivrosNarrativas Económicas:Shiller, R. J. (2019). Narrative economics: How stories go viral and drive major economic events. Princeton University Press.Sobre a economia da indústria musical:Krueger, A. B. (2019). Rockonomics: A backstage tour of what the music industry can teach us about economics and life. Currency.Artigos científicosNetworks (redes) de produção:Carvalho, V. M., & Tahbaz-Salehi, A. (2019). «Production networks: A primer. Annual Review of Economics», 11, 635-663.Acemoglu, D., Carvalho, V. M., Ozdaglar, A., & Tahbaz-Salehi, A. (2012). «The networkorigins of aggregate fluctuations. Econometrica», 80(5), 1977-2016.Grandes empresas e granularidade:Giovanni, J., Levchenko, A. A., & Mejean, I. (2014). «Firms, destinations, and aggregate fluctuations». Econometrica, 82(4), 1303-1340.Gabaix, X. (2011). «The granular origins of aggregate fluctuations». Econometrica, 79(3), 733-772.Links úteisO famoso guardanapo com a Curva de Laffer, no SmithsonianA importância da NOKIA para a FinlândiaO testemunho do CEO da Ford Alan Mulally, ao Congresso dos EUA, em novembro de 2008, no qual explica como o colapso da concorrência poria em causa a existência da própria Ford.As chuvas na Eslovénia e a AutoeuropaUma radiografia das empresas portuguesas (e a importância das grandes)O peso da Autoeuropa na economia portuguesaBIOSMARIANA ALVIMÉ locutora da rádio RFM há 15 anos. Depois de quase 10 a fazer o «Café da Manhã», agora leva os ouvintes a casa, com Pedro Fernandes, no «6PM». É autora de livros para adolescentes e criou o podcast «Vale a Pena», no qual entrevista artistas enquanto leitores.JOSÉ ALBERTO FERREIRADoutorando em Economia no Instituto Universitário Europeu, em Florença. Trabalhou no Banco Central Europeu, com foco na investigação em modelos de política monetária e macroprudencial.

Welcome to another exciting episode of the Mixtape with Scott! Today, I get to have on the show someone who has become something of a friend the last few years, an expert in health economics and social policy, Adriana Lleras-Muney at UCLA, a Professor of Economics at UCLA.Dr. Lleras-Muney's journey in economics is super impressive and even involves traveling through all the alleyways of causal inference. After earning her Ph.D. from Columbia University where she wrote a job market paper on compulsory schooling, at a time where it had just become accepted wisdom that the Angrist and Krueger 1991 article needed a fresh take. She then went to Princeton, the birth place of causal inference in labor, before making her way to UCLA where Guido Imbens had just gotten to, and who is also now one of her coauthors in a new article at the Quarterly Journal of Economics. So when I think about her story, it's hard for me not to hear the echoes, I guess, of the history of causal inference too. Her academic accolades are too many to name, but I'll name a few. She's an associate editor for the Journal of Health Economics and serves on the board of editors for both the American Economic Review and Demography. She's also been a permanent member of the Social Sciences and Population Studies Study Section at the National Institute of Health and an elected member of the American Economic Association Executive committee. In 2017, her contributions to the field were recognized with the prestigious Presidential Early Career Awards for Scientists and Engineers (PECASE).But what really sets Adriana apart is her groundbreaking research. She's been at the forefront of exploring the relationships between socioeconomic status and health, with a particular focus on education, income, and policy. Her recent work has taken a fascinating turn, examining the long-term impact of government policies on children. She's been digging into programs like the Mother's Pension program and the Civilian Conservation Corps from the first half of the 20th century, uncovering insights that are still relevant today. Her work has appeared in all the major journals in economics such as the American Economic Review, Econometrica, The Review of Economic Studies, and the Quarterly Journal of Economics.So, all that said, I hope you find this interview as interesting as I did. The video will be posted most likely later to YouTube; my Scottish hotel has surprisingly very slow internet and I'm still downloading the video, and so will likely be uploading it too all night. But thank you again for all your support. Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

Note:Economists typically think that labor and capital are complementary - more of the one makes the other more productive. But there's a flourishing literature that looks at the consequences of capital that replaces, rather than augments, human workers. In this post, I want to talk about a very simple equation that is inspired by the ideas in these papers, and which I think is a useful thinking tool.This podcast is an audio read through of the (initial version of the) article When the Robots Take Your Job, originally published on New Things Under the Sun.Articles Mentioned:Acemoglu, Daron, and Pascual Restrepo. 2018. The Race between Man and Machine: Implications of Technology for Growth, Factor Shares, and Employment. American Economic Review 108(6): 1488-1542. https://doi.org/10.1257/aer.20160696Acemoglu, Daron, and Pascual Restrepo. 2022. Tasks, Automation, and the Rise in U.S. Wage Inequality. Econometrica 90(5): 1973-2016. https://doi.org/10.3982/ECTA19815Korinek, Anton, and Donghyun Suh. 2024. Scenarios for the Transition to AGI. NBER Working Paper 32255. https://doi.org/10.3386/w32255

Over the last five years, Milan has interviewed authors of big books, that have brought innovative new ideas to the India policy debate.  And he's also interviewed authors of lengthy books. On the show this week, he sits down with an author who's written a big book in every sense of the term.It is no stretch to say that Accelerating India's Development: A State-Led Roadmap for Effective Governance is one of the most important books written about the political economy of India's development. Over 600 pages and 200 pages of notes, it takes readers on an exhaustive deep dive of India's governance challenges, especially in delivering essential public services. The book draws on a wealth of research and practical insights to offer actionable, evidence-based strategies for reforms.The author of this new book is the economist Karthik Muralidharan. Karthik is the Tata Chancellor's Professor of Economics at the University of California San Diego.He is one of the most prolific economists of his generation and his works spans public finance and development economics, with a focus on education, health, welfare, and public service delivery.Milan and Karthik discuss the book's origin story, Karthik's framework for thinking about state capacity, and how to change the incentives of politicians and bureaucrats. Plus, the two discuss some of the book's big ideas, ranging from data collection to public sector contracting and cash transfers.Episode notes:1. Karthik Muralidharan, Niehaus, Paul, and Sandip Sukhtankar, "General Equilibrium Effects of (Improving) Public Employment Programs: Experimental Evidence from India," Econometrica 91, no. 4 (2023): 1261-1295.2. Karthik Muralidharan, Paul Niehaus, and Sandip Sukhtankar, "Integrating Biometric Authentication in India's Welfare Programs: Lessons from a Decade of Reforms," Center for Effective Global Action Working Papers, University of California, 2022.3. Karthik Muralidharan, Paul Niehaus, Sandip Sukhtankar, and Jeffrey Weaver, "Improving Last-Mile Service Delivery Using Phone-Based Monitoring," American Economic Journal: Applied Economics 13, no. 2 (2021): 52-82.4. Karthik Muralidharan, Paul Niehaus, and Sandip Sukhtankar, "Building State Capacity: Evidence from Biometric Smartcards in India," American Economic Review 106, no. 10 (2016): 2895-2929.5. Karthik Muralidharan, “A New Approach to Public Sector Hiring in India for Improved Service Delivery,” India Policy Forum 12, no. 1 (2016): 187-236.

In this episode I'm continuing my investigation into Universal Basic Income as the natural solution to the AI and robotics revolution. One day we should be able to work because we want to improve the world and our situations, and not do it because we are under risk of death. The problem is that the intermediate period between having all of our needs taken care of by our robotic assistants, and having to compete with them for wages to put food on the table is not at all a clear path. My guest today chaired a committee that investigated UBI as an option for the BC government.  Their conclusion was that augmenting current social programs would be a better approach. It's time for The Rational View. David Green is a professor in the Vancouver School of Economics at UBC. His areas of research interest include income inequality, immigration, the impact of technical change on the labour market, and labour market policies. He is a former editor of the Canadian Journal of Economics and an International Research Associate with the Institute for Fiscal Studies in London. He has served on the editorial boards for the American Economic Review and the Journal of Political Economy. His work has been published in leading journals, including Econometrica, the American Economic Review, and the Review of Economic Studies. He was also a member of the BC Expert Panel on Basic Income and has served as the President of the Canadian Economics Association. Support the podcast at Patron.Podbean.com/TheRationalView Join the Facebook discussion @TheRationalView Twix @AlScottRational Insta @The_Rational_View

Welcome to season three of the Mixtape with Scott — a podcast devoted to listening to the stories of living economists and creating an oral history of the last 50 years of the profession. This week's interview is with Wilbert van der Klaauw, economic research advisor in the Household and Public Policy Research Division and the director of the Center for Microeconomic Data with the New York Fed. Wilbert has an interesting story for many reasons. He fits with my longstanding interest in causal inference for his early work on regression discontinuity design, both alone and with Hahn and Todd in their 2001 Econometrica. But I also wanted to hear his story because of his decision to leave academia as a full professor at UNC Chapel Hill to work at the Federal Reserve. (Which again brings to mind that part of the story of the profession is the Federal Reserve itself but that's for another day). So it was a real interesting experience to get to talk with Wilbert and hear more about his life coming from the Netherlands to study at Erasmus, where he met a young Guido Imbens — a detail I didn't know about either — and studied econometrics as his undergraduate major (a major I also didn't know existed apart from economics). So I hope you enjoy this interview! Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

Welcome to this week's episode of the Mixtape, I'm Scott Cunningham, the host. We are in the final stretch! Season two is almost over. When it's all said and done, there'll be 45 episodes in season two, and 34 from season which is [does math on a piece paper, scratches it out, starts over, then announces] 79 episodes. Man, what a fun this has been. Today's interview is with Dr. Jinyong Hahn, the chair of the economics department at University of California Los Angeles and a prominent econometrical. I knew of Dr. Hahn mainly from his 2001 paper in Econometrica with Petra Todd and Wilbert Van der Klauuw on identification and estimation in regression discontinuity designs though he's been extremely prolific just that one. I learned a lot of new things, and you'll hear my surprise as a bunch of things click in place. I just wanted to say again thank you for all your support. I hope you have a great week as we head into the holidays. Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

Rory Cellan-Jones (host) talks to Ingela Alger (IAST) and Flavio Toxvaerd (University of Cambridge) about the drivers of research silos, the merits of conducting interdisciplinary research and how to overcome disciplinary divides. This episode takes a look at why academic research is trapped in research silos. Ingela Alger and Flavio Toxvaerd engage in a thoughtful discussion with Rory Cellan-Jones, to shed light on the challenges faced in conducting interdisciplinary research. They emphasize the significant benefits that interdisciplinarity can bring and share insight into how to foster interdisciplinary research culture for improved results. Listen to this episode on your preferred podcast platformSeason 3 Episode 2 transcriptFor more information about the podcast and the work of the institutes, visit our websites at https://www.bennettinstitute.cam.ac.uk/ and https://www.iast.fr/Tweet us with your thoughts at @BennettInst and @IASToulouse.With thanks to:Audio production - Steve HankeyAssociate production -  Stella ErkerVisuals - Tiffany NaylorMore information about our host and guests:Rory Cellan-Jones was a technology correspondent for the BBC. His 40 years in journalism have seen him take a particular interest in the impact of the internet and digital technology on society and business. He has also written multiple books, including his latest “Always On” which was published in 2021. @ruskin147Ingela Alger is a CNRS Senior Scientist (DR) in Economics, and the current Director of the Institute for Advanced Study in Toulouse (IAST) as well as the Chair of the Department in Social and Behavioral Sciences. Her research, which has been published in international peer-reviewed journals such as the American Economic Review, Econometrica, and PNAS, focuses on the evolutionary foundations of human preferences, when these are transmitted from generation to generation and are subject to selection.  @ingelaalger Flavio Toxvaerd is a Professor of Economics and Public Policy at the Faculty of Economics, University of Cambridge, a Fellow of Clare College and an Affiliated Researcher with the Bennett Institute for Public Policy. He serves as UKRI Policy Fellow in Competition and Productivity Economics with the Competition and Markets Authority. His research and teaching interests are in microeconomics and game theory with applications, including industrial organisation, competition policy and economic epidemiology. @toxvaerd1If you enjoyed this podcast then check out:Crossing Channels S2E5 featuring Sarah Dillon and Manvir Singh: Why are Stories important for society. 

Welcome back to the Mixtape with Scott. I took a little break to let listeners breathe a little, but I'm back with my regular weekly uploads of new interviews with economists as part of my ongoing project (if that's the right word) to listen to and relay the personal stories of economists and then let those stories then mount up and tell a collective story of the profession. Not “the story”, as there is no such thing as “the story”. Just a curated, selected story. But my hope is that some of you hearing it will have more lights along the path. And today I have the pleasure of introducing you to Ariel Pakes, the Thomas Professor of Economics at Harvard University. This was a fun interview. People either know Dr. Pakes very very well, or they only know him by the letter “P”. He is a structural econometrician and theoretical economist in the industrial organization tradition who has made major contributions to econometrics and theory of the firm as well as applied practices in both. He is also the coauthor with Berry and Levihnson on an extremely popular method for estimating demand called “Berry-Levihnson-Pakes model” or BLP for short. When I asked the chief economist at Spotify, Kyle Kretschman, just as the interview was concluding, what paper in economics continues to have had the most lasting impression on him even all these years after grad school, he just smiled and said “BLP”. And that is hardly a minority position. The 1995 Econometrica by those three economists, “Automobile Prices in Market Equilibrium” has had a major effect within economics and outside. Dr. Pakes has made seminal contributions to areas of lasting relevance to our understanding not just of econometrics but also advanced economies like the United States as he has brought great attention to issues around technological innovation, patents and market competition. And we talked about some of this, particularly towards the end, but we talked about it in a way that I think you'll find interesting because we talked into it, we talked through and towards it.You see one of the things that I've been trying to do in these interviews is to get over the “selection on the dependent variable” inherent in our understanding of the published impactful work of others, and the lasting careers others have had. As we look at these people, and we study their works, and we use them even psychologically and existentially in complex barely discernible ways to navigate our own lives, I think we don't always notice that we are usually engaged in a form of extreme selection bias called “conditioning on the outcome variable”. That is, we are only observing these people after the work was done. The failures, the false starts, the experimentations, the experiences they had on that road, how they met their collaborators, how they worked together, how they didn't work so well together, all the trillions of decisions — it isn't that those things are somehow free of endogeneities either. All of life is endogenous, after all. But if we are wanting to better understand how to get from point A to point B in our own lives, I don't think it's all that helpful to just look at people at point C and try to therefore guess where it is we need to reach next. If nothing else, it's at least also helpful to just listen to their story, watch them as they describe the movement as they remember it. And so I loved this interview with Dr. Pakes. Hearing about his love of NBA basketball, the outdoors with his family, and growing up in a radical socialist youth group. His soft spoken, thoughtful discussions of his life as he shared his love for philosophy as a young man and how his first year at Harvard he was straddling economics and philosophy was fascinating, and just learning that his own approach to live — getting himself way over his head on a problem in economics and having to dig a way out — managed to not just get him out, but maybe get the rest of us out too. It was wonderful and this was a really nice interview. I hope you love it as much as me. Thanks again for tuning in. Good luck to all of you as the new semester starts up. My mom got Wordle on the first try this morning. After having played every single morning since day one, this is the first time she actually got it right on the first try. I have decided that not only is this a good omen for the fall, and not only is it good luck for me, but I have decided to share this good luck with all of you. So consider this as my effort to share the blessing with you all no matter where you are. Have a great new semester learning about our awesome, sometimes hard and tragic but always beautiful world full of amazing people. Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

Show notes:Today we tackle a key concept in economics, the idea of market equilibrium, both general and partial. A part of this talk also involves the role of information and that of regulation. We start with polymath Kenneth Joseph Arrow, a key figure in many economic insights. From him we move to a key Chicago school figure and funnyman, George Joseph Stigler. Finally, we star the French economist Gérard Debreu. In season 1 (Danish) we reviewed the history of economic thought before WWII. The coming seasons are dedicated to the Nobel Prize in Economics, and I am joined by economist Otto Brøns-Petersen. The Nobel prize is a good benchmark for how the field and profession of economics developed after WWII. We will focus both on the scientific contributions and on the people behind them. These are all star economists and worthy of your time and attention. Some will mainly feature in one episode, others in several. We therefore advice that you listen in the thematic order we propose – but it is up to you. Rest assured, we will cover all… Eventually.ReferencesKenneth J. Arrow – Prize Lecture. NobelPrize.org. Nobel Prize Outreach AB 2023. Mon. 3 Jul 2023. https://www.nobelprize.org/prizes/economic-sciences/1972/arrow/lecture/Kenneth J. Arrow, Social Choice and Individual Values. Yale University Press, 2012. JSTOR, http://www.jstor.org/stable/j.ctt1nqb90. Kenneth J. Arrow; Gerard Debreu. Existence of an Equilibrium for a Competitive Economy. Econometrica, Vol. 22, No. 3. (Jul., 1954), pp. 265-290.Gerard Debreu – Prize Lecture. NobelPrize.org. Nobel Prize Outreach AB 2023. Mon. 3 Jul 2023. https://www.nobelprize.org/prizes/economic-sciences/1983/debreu/lecture/George J. Stigler – Prize Lecture. NobelPrize.org. Nobel Prize Outreach AB 2023. Mon. 3 Jul 2023. https://www.nobelprize.org/prizes/economic-sciences/1982/stigler/lecture/George J. Stigler – Banquet speech. NobelPrize.org. Nobel Prize Outreach AB 2023. Mon. 3 Jul 2023. https://www.nobelprize.org/prizes/economic-sciences/1982/stigler/speech/George J. Stigler. (2003). Memoirs of an Unregulated Economist. Bibliovault OAI Repository, the University of Chicago Press. George J. Stigler, 1971. "The Theory of Economic Regulation," Bell Journal of Economics, The RAND Corporation, vol. 2(1), pages 3-21, Spring.

Find out more about this event on our website: https://bit.ly/3I4UTdH We show that the premia ills of finance, asset mispricing and short-termism, have a common cause. The problems stem from the commonly adopted, and seemingly prudent practice whereby Giant pension and other institutional funds benchmark short-term performance of their delegated asset managers to market cap indexes or peer group performance. This forces the managers to chase rising prices irrespective of fundamental value, which in turn leads to high volatility of over-valued assets, momentum trading, and over-valuation of the aggregate market. Excessive focus on short-term asset prices obliges corporates to follow suit to the detriment of capital investment and long term growth. The solution will benefit social and investor wealth. Find out more about this event on our website: https://bit.ly/3I4UTdH Interested in watching our webinars live, or taking part in the production of our research? Join our community at: https://bit.ly/3sXPpb5 Paul Woolley's career has spanned the private sector, academia and policy-oriented institutions. He gained his BA and D Phil in Economics from the University of York (UK) and was a Lecturer there in the early 1970's. Following this, he had a long spell at the International Monetary Fund in Washington, latterly heading the division managing the Fund's investment and borrowing activities. He returned to the UK as a Director of Merchant Bank, Baring Brothers. He then founded, and ran for 20 years, the UK arm of GMO, the global fund management business based in Boston, US. He returned to academic life in 2007, funding the Paul Woolley Centre for the study of Capital Market Dysfunctionality at the London School of Economics, where he is a full-time member of the research team. He is a Senior Fellow at the LSE. He has published widely on asset management and related fields in both academic and policy journals throughout his career Dimitri Vayanos is Professor of Finance at the London School of Economics, where he also directs the Financial Markets Group and the Paul Woolley Centre for the Study of Capital Market Dysfunctionality. He is a Fellow of the British Academy, a former Director and Managing Editor of the Review of Economic Studies, a Research Fellow at CEPR and a former Director of its Financial Economics program, a Research Associate at NBER, and a former Director of the American Finance Association. His research, published in leading economics and finance journals, such as Econometrica, the Journal of Finance, the Journal of Financial Economics, the Journal of Political Economy, the Quarterly Journal of Economics, the Review of Economic Studies, and the Review of Financial Studies, focuses on financial markets, and especially on what drives market liquidity, why asset prices can differ from assets' fundamental values, why bubbles and crises can occur, and what are appropriate regulatory and policy responses. He is a co-editor of the book “Beyond Austerity: Reforming the Greek Economy”, a member of the Pissarides Committee, tasked by the Greek government to develop a growth plan for Greece, and co-author of the European Safe Bonds (ESBies) proposal, and a Director of WWF Greece.

Hello Substack readers,I'm excited to share with you the insights from my latest podcast episode, where I had the incredible opportunity to interview Yale professor and renowned economist Steven Berry. In this week's edition, we will:* Introduce you to our esteemed guest, Steven Berry* Delve into the groundbreaking BLP model* Recap the fascinating conversation we hadMeet Steven BerrySteven Berry is the David Swensen Professor of Economics at Yale University, winner of the 1996 Frisch Medal, and a leading figure in the fields of econometrics and industrial organization. With a life that started in the Midwest, Berry's journey into economics was marked by his love for science fiction and the brilliant faculty he studied with at the University of Wisconsin, such as Chuck Manski, Gary Chamberlain, Art Goldberger, John Rust, and many others.The BLP ModelOne of Berry's most significant contributions to the field of economics is the "BLP" model, developed alongside James Levinsohn and Ariel Pakes. Their 1995 Econometrica paper, "Automobile Prices in Market Equilibrium," has had a profound impact on industrial organization and real-world applications.The BLP model offers a powerful tool for understanding demand in various competitive environments, helping both private companies and public policymakers make better decisions. You can find a link to the BLP paper here.Our Conversation with Steven BerryDuring our interview, we explored Berry's life and his experiences in economics. From his early days in the Midwest to his time at Wisconsin and beyond, we delved into the stories and influences that shaped his career. Berry shared his thoughts on the development and real-world applications of the BLP model, as well as his views on the future of industrial organization and econometrics.Our conversation with Berry was a fascinating journey through his life and the evolution of economics over the past few decades. For those who are interested in the intersection of econometrics and industrial organization, or simply curious about the personal stories of an influential economist, this interview is a must-listen.Don't miss the full conversation on this week's episode of the Mixtape with Scott podcast, available on your favorite podcast platform. And as always, be sure to like, share, and subscribe to the podcast, and stay tuned for more "explainers" on econometrics in my Substack.Until next time,Scott CunninghamScott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

Dear Mixtape with Scott listeners,We are pleased to announce the release of our latest podcast episode, featuring an insightful conversation with Jon Roth, an exceptionally talented young econometrician from Brown University. With only three years since graduating, Jon has already made significant contributions to the field of econometrics, publishing high-profile papers on difference-in-differences in esteemed outlets such as Econometrica, Review of Economic Studies, and AER: Insights. Moreover, he has authored a timely literature review on differential timing and has an R&R at JPE: Micro on staggered rollout. In short, he has hit the ground running with many papers that no doubt will be finding their way into all of our papers soon, if they haven't already.In this episode, Jon shares his journey, from growing up in Massachusetts to discovering his passion for economics. He speaks candidly about how his father's accomplishments as a theoretical physicist led him to believe that his potential might lie more in applied labor economics. However, through a series of events, Jon found himself drawn to econometrics, ultimately excelling in the field.We also discussed Jon's love of sports, his transition from solving problem sets to producing research, and his experience navigating the job market over three years, as he honed his professional identity.As a special opportunity for our listeners, Jon Roth will be teaching an exclusive workshop on the Mixtape Sessions platform on Friday, April 21st, starting at 9 am EST. Don't miss the chance to learn from one of the brightest minds in the field, as he covers much of his own work and more.Join me, your host Scott Cunningham, as we dive into the life and work of Jon Roth in this engaging episode of Mixtape with Scott. We hope you enjoy the conversation as much as we did. Youtube video below. As always, we appreciate your support for Mixtape with Scott. If you enjoy our podcast and want to get even more from our community, consider becoming a paying subscriber to our Substack. I am working hard on trying to provide exclusive value for all paying subscribers, so stay tuned. For now it's just the warm glow you'll get from knowing you're contributing!If you haven't already, please take a moment to share this episode with your friends, colleagues, and anyone you think would enjoy it. Your recommendations are incredibly valuable and help us grow our audience. Remember to also like, follow, and subscribe to Mixtape with Scott on your preferred podcast platform to stay updated on our latest episodes. And leave us a review on Spotify or Apple; those always help.Thank you for being a part of our journey as we continue to explore the fascinating stories of the people shaping the world of economics. We look forward to sharing more thought-provoking conversations with you.Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

Imelda Flores Vazquez from Econometrica, Inc. explains how economists use mathematics to evaluate the efficacy of health care policies. When a hospital or government wants to adjust their health policies — for instance, by encouraging more frequent screenings for certain diseases — how do they know whether their program will work or not? If the service has already been implemented elsewhere, researchers can use that data to estimate its effects. But if the idea is brand-new, or has only been used in very different settings, then it's harder to predict how well the new program will work. Luckily, a tool called a microsimulation can help researchers make an educated guess.

What a pleasure it is this week to introduce my guest on the Mixtape with Scott, Dr. Pedro Sant'Anna. Had you asked me a few years ago the likelihood I'd make such a good new friend this late in life, I would not have guessed it, but from countless conversations on social media, and even more in DM on our Slack channel with two other close friends, Pedro Sant'Anna has become one of my favorite people in life. A constantly upbeat, friendly, energetic man, patient to a fault to explain every single detail of econometrics, and enjoying himself as does so, he is one of the best in the profession. He is as many of you know one of the half dozen important young econometricians that have made major contributions to the difference-in-differences research design. His productivity is intense so I can't name them all, but the two I know best, almost by heart, are:* Callaway and Sant'Anna (2021), “Difference-in-differences with multiple time periods” Journal of Econometrics* Sant'Anna and Zhou (2020), “Doubly-robust difference-in-differences estimators”, Journal of EconometricsThe first one has over 2000 cites and it was only published a little over a year ago. He also has an Econometrica with Jon Roth on issues related to functional form and parallel trends in diff-in-diff and a review article (also with Jon Roth, but also with John Poe and Alyssa Bilinski) for anyone who wants to in one stop learn everything you need to know about diff-in-diff. In this mixtape episode, though, we learn more than just his papers. Pedro shares his story with me. I hope you like it and I hope as always you come to value both his story, but also the contemporary ongoing series I'm doing on the many stories of economists. Because to quote, Sue Johnson:“We use stories to make sense of our lives. And we use stories as models to guide us in the future. We shape stories, and then stories shape us.”Consider subscribing, sharing and possibly even supporting the substack as I continue to try and accumulate enough stories of living economists that we have those stories to help us make sense of our lives, but also an oral history of the profession. Thank you again for your support! Youtube below!Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

This week's episode of the Mixtape with Scott is a little out of order. Season two's episodes are going to be a little out of order, based on what feels like the best next episode to present at that time. So I decided after doing my interview with University of Arizona professor of economics, Hide Ichimura, that I wanted to release it because I had such a delightful time talking with him. Dr. Ichimura is an econometrician whose work I've gotten to know more recently because it's been experiencing a little bit of a revival (though it's always remained very popular over the years) within the difference-in-differences literature thanks, in part, to the Sant'anna and Zhao (2020) Journal of Econometrics on robust diff-in-diff, Callaway and Sant'anna (2021) paper on differential timing, and in many ways, other papers that conduct certain kinds of imputations and estimations that are similar in spirit like Borusyak, et al's (2022) robust efficient imputation estimator, and even Abadie and Imbens (2011) selection bias adjustment method if you squint your eyes. I had a wonderful experience talking with Dr. Ichimura today. This is sort of part of my broader interest, as I say in the intro, in interviewing econometricians who were active in the 1990s working on topics in causal inference, and to that end, I had in mine two Restuds by Dr. Ichimura with Heckman and Todd (1997) and a 1998 one in Restud also by Heckman and Todd (and the identical title!!), both on program evaluation. But I also just in general wanted to hear his story, and I'm so glad I did and that he would share it. At the end of the episode, I asked him to share with me a paper that, maybe isn't his favorite, but that has always stuck in his mind. He shared with me Stephen Nickell's 1979 article in Econometrica entitled “Estimating the Probability of Leaving Unemployment”. As always, opening introduction music is by Wes Cunningham (no relation).And don't forget to subscribe, share and maybe even support this! This podcast is subsidized by your donations and my workshops! Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Two very different experiences with ChatGPT, published by Sherrinford on February 7, 2023 on LessWrong. Experience 1: The Vikings in Cuba ChatGPT: Hello! How can I help you today? Me: I have a question on history. When the Vikings landed on Cuba, did that anger the aborigines who already lived there or were the newcomers met with indifference? ChatGPT: There is no historical evidence that Vikings ever landed on Cuba. The Vikings primarily explored and settled in parts of Europe and North America, such as Greenland and present-day Canada. The indigenous peoples of these areas would have likely perceived the Vikings as foreign invaders, but there is no record of Viking contact with the indigenous peoples of Cuba. Me: But if this is true, then what explains the Anti-Viking Discrimination Reform Act in the Cuban constitution? ChatGPT: I apologize, but there is no reference to an "Anti-Viking Discrimination Reform Act" in the Cuban constitution, or any historical record of such legislation related to Vikings in Cuba. It is likely a misinformation or a misinterpretation of some kind. Experience 2: Nash's newsvendor impossibility theorem Me: Can you explain Nash's newsvendor impossibility theorem? ChatGPT: Yes, the newsvendor problem, also known as the Nash's newsvendor theorem, states that it is impossible for a single decision maker to simultaneously optimize both the order quantity and expected profit in the newsvendor problem. The newsvendor problem is a classical inventory management problem where a retailer must decide how much of a perishable item to order and sell before its expiration date, given uncertain demand. The theorem states that there is always a trade-off between ordering too much (resulting in surplus inventory waste) and ordering too little (resulting in lost sales). This trade-off creates a fundamental conflict of interest that can only be resolved by incorporating additional information, such as costs and revenue functions, into the decision-making process. Me: What's the equilibrium implication of that theorem for an oligopoly setting? ChatGPT: In an oligopoly setting, where a few firms compete in a market, the Nash's newsvendor theorem implies that firms will face a trade-off between the quantity they produce and their expected profit. Since the demand for a product is uncertain, each firm must make a decision about how much of the product to produce, knowing that the quantity produced by all firms will impact the market price. In this setting, there is no single best decision that a firm can make, as the optimal quantity to produce depends on the production decisions of all other firms in the market. As a result, firms will typically find themselves in a Nash equilibrium, where each firm is making the best decision it can given the decisions of all other firms. In this equilibrium, each firm may not be optimizing its expected profit, as the trade-off between quantity and expected profit creates a fundamental conflict of interest for all firms. The Nash's newsvendor theorem highlights the importance of considering market dynamics in addition to individual firm decision making in order to understand the behavior of oligopolies and to make more informed decisions about production and pricing strategies. Me: Can you tell me a bit more about Nash's newsvendor impossibility theorem? When was it published, and in which journal? ChatGPT: John Nash's newsvendor impossibility theorem was first published in a 1955 paper titled "The Bargaining Problem" in the journal Econometrica. In this paper, Nash introduced the concept of the newsvendor problem and showed that it was impossible for a single decision maker to simultaneously optimize both the order quantity and expected profit. The newsvendor problem is a classical inventory management problem where a retail...

Tymofiy Mylovanov, president of the Kyiv School of Economics (KSE), and Nataliia Shapoval, head of KSE Institute, discuss how their research priorities have shifted during the war on Ukraine, how the University has operated throughout these challenging times, and why the higher education system is integral to Ukraine's future. This episode is hosted by Rory Cellan-Jones (former technology correspondent for the BBC), and features guest experts Tymofiy Mylovanov (Kyiv School of Economics) and Nataliia Shapoval (Kyiv School of Economics). Listen to this episode on your preferred podcast platform: https://pod.fo/e/15661fSeason 2 Episode 4 transcript: https://www.bennettinstitute.cam.ac.uk/wp-content/uploads/2022/12/CC-S2-ep4-transcript.pdf Relevant linksListen to our first episode on Ukraine with Nataliia Shapoval here: Ukraine Invasion: context, consequences and the information war.Keep up to date on events in Ukraine by following the Kyiv School of Economics @kse_ua, the Kyiv Institute @KSE_Institute, Tymofiy Mylovanov's daily morning and evening updates @Mylovanov and Nataliia Shapoval @Nataliia_Shapo.The Kyiv School of Economics, together with Ukrainian businesses and state-owned companies, have launched a humanitarian aid campaign for Ukraine. You can also help (link to KSE website). Tweet us with your thoughts at @BennettInst and @IASToulouseAudio production by Steve Hankey.Associate production by Stella Erker. Visuals by Thomas Devaud. More information about our guests:Tymofiy Mylovanov is the President of Kyiv School of Economics, Associate Professor at the University of Pittsburgh and former Minister of Economic Development, Trade and Agriculture of Ukraine. He received his M.A. in Economics from KSE and earned his Ph.D. in Economics from the University of Wisconsin Madison. Tymofiy's research interests cover such areas as theory of games and contracts, and institutional design. His articles on these topics have been published in the leading international academic magazines, including Econometrica, American Economic Review, the Review of Economic Studies. @Mylovanov @kse_uaNataliia Shapoval is the Vice President for Policy Research and Director of the Center of Excellence in Procurement at the Kyiv School of Economics in Ukraine. She worked on policy research projects on public health's cost and resource allocation, and on youth unemployment in Ukraine and Europe. She is also a member of the Editorial Board of Vox Ukraine, and a contributor to the Ukraine reform monitoring project of the Carnegie Endowment for International Peace. @Nataliia_Shapo @KSE_InstituteRory Cellan-Jones is a former technology correspondent for the BBC. His 40 years in journalism saw him take a particular interest in the impact of the internet and digital technology on society and business. He has written multiple books, including his latest “Always On” wh

The world is a highly competitive place, and becoming successful requires hard work, dedication, and luck. This is the view of today's guest, Professor Robert Frank, who helps us unravel the nuance of conspicuous consumption trends and the role of luck in gaining financial success. Professor Frank is the emeritus Henrietta Johnson Louis Professor of Management at Cornell University and holds an MA in statistics and a Ph.D. in Economics from UC Berkeley. He is also a prolific author, having written 12 books, financial textbooks, and many peer-reviewed articles in journals such as the American Economic Review, Econometrica, and Journal of Political Economy. He is passionate about how policy can help drive positive consumer behaviour, reduce inequality, and increase individual happiness. His work has also focused on the role of luck in achieving financial success which he covers in his book Success and Luck. In this episode, we unpack how individuals can improve societal collective action, the role of policy in driving those changes, and how luck interplays with success. We discuss economic and financial relativism, the dangers of conspicuous consumption, how expenditure cascades occur, and what influences consumption trends in society. We also dive into the topic of luck, whether wealthy people are happier, what behavioural changes are needed to create a better society, and more.   Key Points From This Episode:   Professor Frank describes the difference between departures from rational choice with regret and without regret. (0:04:34) Whether he classifies his work as behavioural economics. (0:07:38) An explanation of economic and financial relativism. (0:10:50) The role of economic and financial relativism in consumption trends. (0:12:44) Find out what constitutes a positional good. (0:16:56) How the consumption of positional goods affects psychological well-being. (0:19:32) Why people choose to engage in consumption arms races. (0:21:52) The relationship between the consumption of luxury goods and happiness. (0:24:45) What people can do to recognize and avoid negative consumption behaviours. (0:26:31) How the spending of the super-rich impacts the spending habits of the typical consumer. (0:27:38) Ways in which social media influencers have affected consumption. (0:30:32) We learn about the link between consumption and inequality. (0:32:40) How well differences in human capital explain differences in income. (0:35:04) Professor Frank explains how likely it is that the most skilled person gets the best outcome in a competitive market. (0:38:13) Professor Frank shares how they measure luck. (0:41:20) The influence luck has on achieving a successful outcome. (0:42:09) Find out if luck influences consumption trends and inequality. (0:44:03) A thought experiment concerning the wealthy and higher taxes. (0:46:56) We discuss whether winner-take-all markets are a good thing for society. (0:50:22) How people should behave differently to help drive positive change. (0:53:06) Advice for people to stay motivated and work hard. (0:57:19) What Professor Frank thinks about working a job you hate for more money. (0:58:59) He provides insight for people who work jobs they hate. (0:59:59) His approach on the subject of luck and meritocracy with young kids. (1:00:47) We discuss the idolization of financially successful people. (1:03:36) How successful individuals should behave differently in an economy where luck plays such an important role. (1:05:38) The response of successful people to Success and Luck. (1:08:15) Steps people can take to positively affect those around them. (1:09:29) Discover what Professor Frank's position is on policy. (1:14:20) We hear how Professor Frank defines success in his life. (1:18:33)     Links From Today's Episode:   Professsor Robert Frank on Twitter — https://twitter.com/econnaturalist Cornell University — https://www.cornell.edu/ Success and Luck — https://www.amazon.com/Success-Luck-Good-Fortune/ Luxury Fever — https://www.amazon.com/Luxury-Fever/ Principles of Economics — https://www.amazon.com/Principles-Economics/ The Winner-Take-All Society — https://www.amazon.com/Winner-Take-All-Society/ American Economic Review — https://www.aeaweb.org/journals/aer Econometrica — https://onlinelibrary.wiley.com/journal/14680262 Journal of Political Economy — https://www.jstor.org/journal/jpoliecon Project Sunroof — https://sunroof.withgoogle.com/ Rational Reminder on iTunes — https://itunes.apple.com/ca/podcast/the-rational-reminder-podcast/id1426530582. Rational Reminder Website — https://rationalreminder.ca/ Rational Reminder on Instagram — https://www.instagram.com/rationalreminder/?hl=en Rational Reminder on YouTube — https://www.youtube.com/channel/ Benjamin Felix — https://www.pwlcapital.com/author/benjamin-felix/ Benjamin on Twitter — https://twitter.com/benjaminwfelix Benjamin on LinkedIn — https://www.linkedin.com/in/benjaminwfelix/ Cameron Passmore — https://www.pwlcapital.com/profile/cameron-passmore/ Cameron on Twitter — https://twitter.com/CameronPassmore Cameron on LinkedIn — https://www.linkedin.com/in/cameronpassmore/

Chris Nosko is a PhD economist. He did his PhD in economics at Harvard in the mid 2010s before going to Chicago Booth take a job as an assistant professor. But for a year prior to taking that job, between Harvard and Chicago, he did a postdoc fellowship at eBay where he, Thomas Blake and Steve Tadelis met and worked together on a project involved a serendipitous event at the company in which eBay quit paying for branded key words (e.g., “eBay Volvo decals”, “eBay typewriters”) on some but not all search engine auctions. They asked for the data on traffic to the site before and after eBay quit paying for branded keywords for all search engines (both those they kept paying and those they didn't), ran a simple event study diff-in-diff and found evidence that search engine marketing at eBay was perhaps not causing increased traffic to the site. They convinced management to field a large RCT which confirmed their diff-in-diff results, and that study was published in Econometrica. Not a shabby way to start a career as an economist. For many of us, a PhD in economics from Harvard, a successful partnership with eBay resulting in a study destined for a Top 5 and a tenure track job at Chicago Booth meant staying at Booth and having a career as an academic. No one outrightly says that the only meaningful life you can have as an economist is to be an academic, as it's vulgar, opinionated and obviously false to talk that way about how someone else should live their life, but the norms are pretty powerful nonetheless. Well, starting around the time that Chris got his job at Booth, tech began experiencing a surge in hiring of PhD economists, largely driven by Amazon's nearly insatiable appetite for them. Talking with people at Amazon, I have learned that behind this push was Pat Bajari, and behind Pat Bajari was Jeff Bezos who had long believed economics, and economists more specifically, had unique value. As Susan Athey said to me, though, in an interview earlier, Bajari though had to do pull a rabbit out of a hat. Whereas the first wave of economists to tech — people like Hal Varian, Susan Athey, Preston McAfee — had largely been micro theorists helping craft the foundations of a business model through auctions and advertising that would support search engines, arguably the core arteries of the internet itself — Bajari would have the task of bringing in young people, fresh out of grad school, and in Athey's words, make them productive. And one of the people Bajari would ultimately tap do that was Chris Nosko, an assistant professor at Chicago Booth and someone trained in structural industrial organization, one of the economics' more interesting experiments of fusing deep microeconomic theory with econometric estimation. Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.Nosko was a Ariel Pakes student at Harvard and was well versed in so many different parts of economics and modern technology that it almost seems predestined that he would ultimately leave Chicago Booth permanently and go to Amazon when Bajari finally convinced him to, but that's all selection on the dependent variable reasoning. When we look back in time at decisions we made, our mind tends to forget that there was a moment when we could've gone left instead of right. The same with Chris — there was a decision that had to be made to leave a career as an academic. The decision materialized into what it materialized, but to pretend it was easy, or that it didn't have risk, or that Chris didn't try to manage that risk in some ways is really unfair to our earlier selves or even our future selves who are in situations facing, not probabilistic risk but more like Knightian uncertainty in which no one truly has a clue what possibly could happen. But Chris did leave. Sort of. He took “a leave of absence” from Booth in 2015 and took a job at Amazon, then permanently left Booth in 2016. He spent four years at Amazon before leaving for Uber, one of the more impressive firms to ever exist for creating an actual open marketplace solving two sided matching problems through algorithms and prices. Algorithms, prices and rules — three ways, no doubt there are others, in which modern economies coordinate productive activity. Is it really so surprising that economics might be valued by tech firms given the complex coordination they try to solve using all three?Thank you for reading Scott's Substack. This post is public so feel free to share it.Chris has been at Uber for four years. He is now Vice President and Head of Science and Analytics for Uber Product there.  Within tech, economists sort into tons of different jobs with titles that to an academic don't make a ton of sense — just like so much of what academics' lives takes place within administrative units that make little sense to anyone else. If Chris isn't the chief economist, though, at Uber, I figure he's probably up there. And he's my guest this week on The Mixtape with Scott as part of my longer, unfolding series I call “Economists in tech”. Our conversation covered a lot of ground. We talked about growing up in rural Oregon, falling into programming early on and working a few years between high school and college during the early wave tech boom of the late 1990s and early 2000s as a programmer. It wasn't exactly what he would do later, as that was more web design and less machine learning and statistics, but the aptitude of programming is very portable and his deep knowledge of tech sectors was anyway established or at least re-invested in while there. We talked about his love for his liberal arts education at the University of Chicago where he did his undergraduate degree, and his broad navigation of economics as a field and a career.  All in all, it was a fun opportunity to talk to Chris, to learn more about his own path, about the world out there outside of academia, what economists do in tech, and how all of these things fit together for both economics but maybe more importantly just for Chris himself. I think a lot of people are going to find Chris's story very interesting and personally intriguing as they may see him in themselves. You can read some of Chris's work here. Thanks again for tuning in! I hope you enjoy this week's interview as much as I did! If you are enjoying these, please consider supporting me by sharing the podcast and/or becoming a paying subscriber!Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

Chris Nosko is a PhD economist. He did his PhD in economics at Harvard in the mid 2010s before going to Chicago Booth take a job as an assistant professor. But for a year prior to taking that job, between Harvard and Chicago, he did a postdoc fellowship at eBay where he, Thomas Blake and Steve Tadelis met and worked together on a project involved a serendipitous event at the company in which eBay quit paying for branded key words (e.g., “eBay Volvo decals”, “eBay typewriters”) on some but not all search engine auctions. They asked for the data on traffic to the site before and after eBay quit paying for branded keywords for all search engines (both those they kept paying and those they didn't), ran a simple event study diff-in-diff and found evidence that search engine marketing at eBay was perhaps not causing increased traffic to the site. They convinced management to field a large RCT which confirmed their diff-in-diff results, and that study was published in Econometrica. Not a shabby way to start a career as an economist. For many of us, a PhD in economics from Harvard, a successful partnership with eBay resulting in a study destined for a Top 5 and a tenure track job at Chicago Booth meant staying at Booth and having a career as an academic. No one outrightly says that the only meaningful life you can have as an economist is to be an academic, as it's vulgar, opinionated and obviously false to talk that way about how someone else should live their life, but the norms are pretty powerful nonetheless. Well, starting around the time that Chris got his job at Booth, tech began experiencing a surge in hiring of PhD economists, largely driven by Amazon's nearly insatiable appetite for them. Talking with people at Amazon, I have learned that behind this push was Pat Bajari, and behind Pat Bajari was Jeff Bezos who had long believed economics, and economists more specifically, had unique value. As Susan Athey said to me, though, in an interview earlier, Bajari though had to do pull a rabbit out of a hat. Whereas the first wave of economists to tech — people like Hal Varian, Susan Athey, Preston McAfee — had largely been micro theorists helping craft the foundations of a business model through auctions and advertising that would support search engines, arguably the core arteries of the internet itself — Bajari would have the task of bringing in young people, fresh out of grad school, and in Athey's words, make them productive. And one of the people Bajari would ultimately tap do that was Chris Nosko, an assistant professor at Chicago Booth and someone trained in structural industrial organization, one of the economics' more interesting experiments of fusing deep microeconomic theory with econometric estimation. Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.Nosko was a Ariel Pakes student at Harvard and was well versed in so many different parts of economics and modern technology that it almost seems predestined that he would ultimately leave Chicago Booth permanently and go to Amazon when Bajari finally convinced him to, but that's all selection on the dependent variable reasoning. When we look back in time at decisions we made, our mind tends to forget that there was a moment when we could've gone left instead of right. The same with Chris — there was a decision that had to be made to leave a career as an academic. The decision materialized into what it materialized, but to pretend it was easy, or that it didn't have risk, or that Chris didn't try to manage that risk in some ways is really unfair to our earlier selves or even our future selves who are in situations facing, not probabilistic risk but more like Knightian uncertainty in which no one truly has a clue what possibly could happen. But Chris did leave. Sort of. He took “a leave of absence” from Booth in 2015 and took a job at Amazon, then permanently left Booth in 2016. He spent four years at Amazon before leaving for Uber, one of the more impressive firms to ever exist for creating an actual open marketplace solving two sided matching problems through algorithms and prices. Algorithms, prices and rules — three ways, no doubt there are others, in which modern economies coordinate productive activity. Is it really so surprising that economics might be valued by tech firms given the complex coordination they try to solve using all three?Thank you for reading Scott's Substack. This post is public so feel free to share it.Chris has been at Uber for four years. He is now Vice President and Head of Science and Analytics for Uber Product there.  Within tech, economists sort into tons of different jobs with titles that to an academic don't make a ton of sense — just like so much of what academics' lives takes place within administrative units that make little sense to anyone else. If Chris isn't the chief economist, though, at Uber, I figure he's probably up there. And he's my guest this week on The Mixtape with Scott as part of my longer, unfolding series I call “Economists in tech”. Our conversation covered a lot of ground. We talked about growing up in rural Oregon, falling into programming early on and working a few years between high school and college during the early wave tech boom of the late 1990s and early 2000s as a programmer. It wasn't exactly what he would do later, as that was more web design and less machine learning and statistics, but the aptitude of programming is very portable and his deep knowledge of tech sectors was anyway established or at least re-invested in while there. We talked about his love for his liberal arts education at the University of Chicago where he did his undergraduate degree, and his broad navigation of economics as a field and a career.  All in all, it was a fun opportunity to talk to Chris, to learn more about his own path, about the world out there outside of academia, what economists do in tech, and how all of these things fit together for both economics but maybe more importantly just for Chris himself. I think a lot of people are going to find Chris's story very interesting and personally intriguing as they may see him in themselves. You can read some of Chris's work here. Thanks again for tuning in! I hope you enjoy this week's interview as much as I did! If you are enjoying these, please consider supporting me by sharing the podcast and/or becoming a paying subscriber!Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Substack at causalinf.substack.com/subscribe

The Cognitive Crucible is a forum that presents different perspectives and emerging thought leadership related to the information environment. The opinions expressed by guests are their own, and do not necessarily reflect the views of or endorsement by the Information Professionals Association. During this episode, Prof Matt Jackson of Stanford University discusses social learning, game theory, and an optimization methodology for minimizing the spread of disinformation.  Research Question:  There's a difference between entertainment and becoming informed.  How do we produce systems which are both entertaining & informing? Resources: Matt Jackson's Stanford Web Page Learning through the grapevine and the impact of the breadth and depth of social networks by Matthew O. Jackson, Suraj Malladi, and David McAdams The Human Network by Matthew Jackson Measuring Group Differences in High-Dimensional Choices: Method and Application to Congressional Speech by Matthew Gentzkow, Jesse M. Shapiro, and Matt Taddy The Secret of Our Success: How Culture Is Driving Human Evolution, Domesticating Our Species, and Making Us Smarter by Joseph Henrich Link to full show notes and resources https://information-professionals.org/episode/cognitive-crucible-episode-116 Guest Bio:  Matthew O. Jackson is the William D. Eberle Professor of Economics at Stanford University and an external faculty member of the Santa Fe Institute. He was at Northwestern University and Caltech before joining Stanford, and received his BA from Princeton University in 1984 and PhD from Stanford in 1988. Jackson's research interests include game theory, microeconomic theory, and the study of social and economic networks, on which he has published many articles and the books `The Human Network' and `Social and Economic Networks'. He also teaches an online course on networks and co-teaches two others on game theory. Jackson is a Member of the National Academy of Sciences, a Fellow of the American Academy of Arts and Sciences, a Fellow of the Econometric Society, a Game Theory Society Fellow, and an Economic Theory Fellow, and his other honors include a Guggenheim Fellowship, the Social Choice and Welfare Prize, the von Neumann Award from Rajk Laszlo College, an honorary doctorate from Aix-Marseille University, the Jean-Jacques Laffont Prize from the Toulouse School of Economics, the B.E.Press Arrow Prize for Senior Economists, the BBVA Frontiers of Knowledge Award in Economics, Finance, and Management, and teaching awards. He has served on the editorial boards of Econometrica, Games and Economic Behavior, PNAS, the Review of Economic Design, and as the President of the Game Theory Society. About: The Information Professionals Association (IPA) is a non-profit organization dedicated to exploring the role of information activities, such as influence and cognitive security, within the national security sector and helping to bridge the divide between operations and research. Its goal is to increase interdisciplinary collaboration between scholars and practitioners and policymakers with an interest in this domain. For more information, please contact us at communications@information-professionals.org. Or, connect directly with The Cognitive Crucible podcast host, John Bicknell, on LinkedIn. Disclosure: As an Amazon Associate, 1) IPA earns from qualifying purchases, 2) IPA gets commissions for purchases made through links in this post.

This week, host Eamon interviewed Dr. Theodore Papageorgiou, the Felter Family Associate Professor of Economics at Boston College. Dr. Papageorgiou specializes his research in labor economics, macroeconomics, and economics of transportation, and his article published in March, 2020, titled “Geography, Transportation, and Endogenous Trade Costs” was awarded the Frisch Medal of the Econometric Society for the best applied paper published in the Econometrica. In this episode, Dr. Papageorgiou discusses the overlooked economic importance of the trade sector, his process of modeling the efficiency of bulk ships in the global market, the factors that cause countries to be mass net exporters and importers, and even the possibility for an “Uber-like” app for freight shipping. Check back in next week for new episodes!

In this week’s episode of The Mixtape with Scott, I had the pleasure of interviewing Kyle Kretschman, Head of Economics at Spotify. It was a great opportunity for me because Kyle is one of the first economists I have spoken to who didn’t enter tech as a senior economist (e.g., John List, Susan Athey, Michael Schwarz, Steve Tadelis). Kyle entered tech straight out of graduate school. He spent much of his career at Amazon, a firm that has more PhD economists than can be easily counted. Under Pat Bajari’s leadership there, Kyle grew and his success was noticed such that he was then hired away by Spotify to lead up their economics team. At the end of the interview, I asked Kyle an economics article that has haunted his memories and he said “BLP”, which is affectionate shorthand that “Automobile Prices in Market Equilibrium” by Berry, Levinsohn and Pakes 1995 Econometrica goes by. I really enjoyed this interview, and despite the less than ideal sound quality at times, I hope you will too.But before I conclude, I wanted to share some more of my thoughts. This series I’ve been doing on “economists in tech”, which has included interviews with John List, Susan Athey, Michael Schwarz and Steve Tadelis, comes from a complex place inside me. First there is the sheer curiosity I have about it as a part of the labor market for PhD economists. As I have said before on here, the tech sector has exploded in the last decade and the demand for PhD economists has grown steadily year over year. Tech demand selects on PhD economists with promising academic style research inclinations. There is substantial positive selection in this market as firms seek out strong candidates can be produce value for them. This is reflected in both junior market salaries, but also senior. Job market candidates are economists with technical skills in econometrics and economic theory, not to mention possess competent computer programming skills in at least one but often several popular coding languages. They are also candidates who were often entertaining careers within academia at the time they entered tech, and in those academic careers, they envisioned themselves writing academic articles about research they found personally and scientifically important and meaningful. Going into tech, therefore, would at least seem to involve choice that may go far beyond merely that of taking one job over another. It may involve a choice between a career in academia and a career outside it, which for many of us can feel permanent, as though we are leaving academia. And for many economists, it may be the first time they have ever contemplated such a thing. If they do internalize the story that way, if they do see taking a job in tech as “leaving academia”, then I can imagine that for at least some economists, that may be complicated, at least. But there’s another reason I have been wanting to talk to economists in tech and that is I am very concerned about the welfare of our PhD students. In a recent article published in the Journal of Economic Literature, economists interviewed graduate students in top economics programs. They found there incredibly high rates of depression, anxiety, loneliness and even suicidality. This is a common feature of graduate studies, but it is interesting that PhD economists have incredibly good employment opportunities and yet the depression and anxiety plague there too. One of the things that struck me in that study was the disconnect between what graduate students felt about their work and what their advisors felt about their own work. Many students, for instance, do not feel they are properly supported by advisers, do not believe their advisers care about their research success and do not even care about them as a person. Whereas most Americans (and faculty) feel that their work has a positive impact on society, only 20% of PhD students in economics feel that way. (I discussed the article as well as my own research on the mental health of PhD students here.) I suppose part of me feels a great sigh of relief to see the labor market for PhD economists expanding in light of those troubling statistics. If students know that life is full of infinite possibilities, then perhaps they can begin to process earlier what they want to do in the short years they have on this small spinning ball of rock we call Earth. If students do not in the end want to become professors, if they do not have the opportunities to become one, they should know that there is no “failure” involved there. Careers are just that — careers. They do not tell us who we are. The sooner a student can detach from the unhelpful story that our value is linked to a vita listing our accomplishments, the sooner they can begin their own life work of choosing their meaning. Can having more labor market opportunities with more employers competing for them help do that? Well no, not really. At least, not exactly. It can disrupt certain equilibrium, but then the new equilibrium can just as easily cover that up too. Still, I do like the idea that to keep students in academia, universities and departments must fight harder for them, pay attention to them, and invest in them as people. I like the idea that students have more options and that the options are diverse. Will it help their depression? Well, that’s another matter, as that’s complex. And presumably the economists in the survey I mentioned were themselves well aware of the career options they had since they were coming from the nation’s top 10 PhD programs in economics. I suppose my point is that ultimately, the burden of life really cannot be resolved with money or career. We are trained to look there because we have boundless appetites. But ultimately the hard work of navigating life can only be helped so much by a job. We must still decide for ourselves what meaning we will choose for ourselves. But one thing I know, and one thing which I think our profession is profoundly bad at saying out loud, is that if we make our identity connected to vitas, we will not just be miserable, we will be hopeless, and probably poisoned. Such a mindset leads to endless laps on a brutalizing treadmill of meaningless performance in which a person chases for first place in a race they don’t remember signing up for and which they cannot win. They compare themselves with others running, not knowing that they too are brutalized by their own treadmill, not realizing that it is impossible to catch up with someone else as there is always someone else ahead of us. The sooner we learn that the joy we long for will not come when we get a top 5, the sooner we can look elsewhere. It has taken me many years to relearn a lesson I learned decades ago — I am whole now. I am complete now. I still run, and I still chase, but I am not chasing completeness. I am not chasing my own wholeness. Being whole and complete has nothing to do with a career. Careers are ultimately orthogonal to hope, which does not mean they do not matter — they absolutely matter. But if asked to deliver meaning, we will find that our jobs are as weak as wet spaghetti at such a task as that.So, I suppose in some ways I simply want to announce — there are incredible opportunities for economists inside government, commerce and academia. But the weight of this life is not likely to be lighter in any one of them, for the weight we feel in life is largely self imposed, inside us, in the stories we tell about who we are and for many of us who we are not. Those stories are real, because we feel them and because we believe them, but they are not true. All stories are wrong, but some are useful, and the story that our lives can only matter if we have certain types of jobs or certain types of success, while it may be useful to getting a paper out or accomplishing something important, in a much bigger sense it is hollow at best and pure poison at worst. TRANSCRIPTThis transcript will be updated once the more complete transcript is finished; for now it was transcribed using voice-to-text machine learning.Kyle Kretschman:Might not have prepared myself well enough to be attractive for some of the most pop most top tier schools. Scott Cunningham:In this week's episode of the mix tape with Scott, I had the pleasure of interviewing Kyle kretchma the head of economics at the streaming platform. Spotify. Before I dive into the interview, though, I wanted to give you a bit of a heads up about the sound quality. Unfortunately, the sound quality in the interview on Kaza side is a bit muffled. We discussed refilming. It tried to find a way to tweak it, but there were certain constraints on the actual sound itself that kept us from being able to do it. And we didn't feel that refilming, it would be good because we thought that the interview had a lot of serendipitous kind of spontaneous tangents and things spoken about that. We thought students and people in academia would want to know, would need maybe even need to know. And I doubted that I could recreate it, cuz I don't even know why it happened. Scott Cunningham:So I'm gonna post a video version of this at my subs, for those who feel that a video version would help them kind of follow it in so far as the audio might be at times challenging. So check out the subst for those of you that wanna watch, watch it instead of just listen to it, hopefully that'll help. I won't say much here by way of introduction, except to say a few things about Kyle, because I wanted to let Kyle tell you his story in his own words, cuz it's his story to tell. And it's an interesting story. Kyle's a PhD economist though from the university of Texas Austin, which is down the road from where I live and work at Baylor, where he wrote on topics in graduate school and applied econometrics, empirical industrial organization or empirical IO and public choice after graduating, Kyle went to Amazon, not academia. Scott Cunningham:In fact, given we might start the boom of tech hiring PhD economists in the early to mid 20 2010s. You could say Kyle maybe was sort of one of the earlier hires among that second wave of PhD economists that went there. He worked for several years at Amazon before being hired away by Spotify to head up and lead a new economics team there, perhaps this is part of a broader trend of tech firms building up more internal teams, not just of data scientists, but like Amazon departments of economists who knows recall though from an earlier interview with Susan athe where, when I asked Susan why she said pat Maja had done something amazing at Amazon, she said he made economists productive. And in time he made many of them productive and very in productive from what I've been able to follow. And Kyle is from what I can gather someone whose skills matured and deepened under the leadership of Papa jar at Amazon and other leaders at and other economists at Amazon. Scott Cunningham:And he was ultimately hunted down by a major tech term to create an economics team there I'm by no means an expert on the labor market for PhD economists. I just have been very intrigued and curious by the, the, the Mar the labor market for PhD economists in tech, because well, partly because of realizing first that cause of inference was really valued in tech, but then to sort of realize that there was just this very large community of economists there, but I don't think it's controversial to say over the last 10 to 15 years, the tech industry really has been disruptive in the labor market for PhD economists. They continue to hire at the junior and senior market in larger and larger volume selecting more and more on people who likely would've gone into academia into tenure track or tenured positions. They pay very high wages, some of the very, some of the highest wages in the country, both at the junior level and especially at the, at the higher end at the, at the more advanced levels, people can earn compensation packages by the, in the, by the time they're in their thirties, that many of us didn't know were possible. Scott Cunningham:It's in my mind, historically novel, and I might be wrong about this, but it, it seems historically novel that the PhD economists who likely would've produced academic research papers in tenured and tenure track jobs have begun to branch out of academia, but maintain those skills and maintain that research output. It's partly driven best. I can tell, buy Amazon, I might be wrong, but by Amazon and paja, as well as Jeff Bezos own view, that economists are what I guess we would just say value added for many firms. Therefore I'm continuing to wanna speak with economists in tech to help better trace out the story. This interview with Kyle follows on the back of earlier interviews with people in tech like John list, you know, a, a distinguished professor of economics at the university of Chicago, but also the former chief economist that Lyft and Uber now Walmart Michael Schwartz, former professor of economics at Harvard. Now, chief economist at Microsoft and Susan athe former chief economist at Microsoft professor at Stanford and now chief economist at the DOJ. I hope you find this to be an interesting dive into the industry. Learn a little bit more about economists there, but by, by learning the about one particular important economist, there a, a young man named Kyle crutch, head of economics at Spotify, my name's Scott Cunningham. And this is the mix tape with Scott. Scott Cunningham:Well, it's my pleasure today to have, as my guest on the mix tape with Scott, Kyle crutch, Kyle, thanks so much for being on the call. Kyle Kretschman:Hey Scott, thanks for having me really appreciate the time to talk Scott Cunningham:Well before we get started with your career and, and everything. I was wondering if you could just tell us your name and your title and where you work. Kyle Kretschman:Sure. Yeah. As you said, I'm Kyle kretchma, I'm the head of economics at Spotify, Scott Cunningham:Head of economics at Spotify. Awesome. Okay. I can't wait to talk. So let me, let me, let's get started. I was wondering if you could just tell me where you grew up. Kyle Kretschman:Sure. So most of the time I grew up in outside of Pittsburgh, Pennsylvania, about an hour north of the city, real real small town probably had one stop light. And maybe the, the funny story that I can share is what I took my wife there. She asked where's the Starbucks. And I said, no Starbucks here. There's no Scott Cunningham:Starbucks. Kyle Kretschman:Yeah. So pretty small town called Chippewa township in Pennsylvania. Scott Cunningham:Oh, okay. Is that near like Amish stuff or anything like that? Kyle Kretschman:No, that's the other side of the state. So this would be Western Pennsylvania about near the end of the turnpike, about five minutes from the Ohio border. Scott Cunningham:Oh, okay. Okay. You said, but you, did you mention, you kind of grew up in different places? Kyle Kretschman:Yeah. So before that, my father worked in civil engineering and so would do build roads and bridges basically across every, across the nation. So I was actually born in Louisiana, lived there with, I think for a whole two, three weeks. I don't quite remember. Cause I was pretty young obviously, but then Michigan and then spent some time in Philadelphia before moving out to Pittsburgh around second grade. Scott Cunningham:Oh, that's kinda like, that's like when people described their parents being in the military, just kind of moving around a lot. Kyle Kretschman:Yeah. A little bit. So, but Scott Cunningham:Then you settled in the second grade Kyle Kretschman:That's right. Yeah. So outside of Pittsburgh and then stayed in Pittsburgh through high school and even through undergrad. Scott Cunningham:Oh, okay. Oh, you went to undergrad in Pennsylvania. Kyle Kretschman:Yeah, I did. So I went to undergrad at the university of Pittsburgh. Oh, okay. It was, yeah. If, I guess maybe continuing the story growing up in a town with no Starbucks. I was, I was pretty intrigued by going to a city. Yeah. And find out that lifestyle and yeah, we might have lived pretty close, like an hour away, but we didn't go down to the city very much. So Pittsburgh was just really, really enticing for a city to, for, to go to undergrad in. And so I basically looked at all schools that were in cities and so the proximity plus then the, the ability to just spread my wings and explore what it's like to be in a city was really, really enticing. Scott Cunningham:Did any of your friends go to pit with you? Kyle Kretschman:Yeah, so there's probably, I grew, I graduated from a class of about a little over 200 people in high school and I think there was like five or six people from high school that went to pit for my class. So definitely had some really good friends who went and kept in touch with, through undergrad. Scott Cunningham:Mm. Yeah. So it wasn't, were you sort of an early generation or you weren't, were you a first generation college student in your family or did your parents go to college Kyle Kretschman:Combination? So my dad went to Penn state civil engineer, as I mentioned, me and my mom actually graduated from undergrad the same week. So my mom went back to school later in life after me, after we went to school. And so yeah, we, we were able to celebrate graduation cuz she went to a small private school right outside of the city also. Scott Cunningham:Oh, okay. Okay. Yeah. Well, so what did you like to do in high school? Kyle Kretschman:So I played a lot of sports before high school and then I kind of switched into, and this was a traditional sports of football, basketball, baseball, but then I switched into tennis in high school. And so that kept me busy, but along with a lot of academics and really, really liked computer science. So played a lot of video games growing up, really enjoyed like that aspect in combination. Scott Cunningham:What games were your, were you, did you play on a, on a video game, plat platform? Like an Nintendo or did you play? Kyle Kretschman:Yeah, no, we played a lot of plays very much into like role playing games. Some of the arcade games like Marvel versus Capcom. So yeah. Yeah. Very, very interested in gaming. Yeah. Maybe I was a little too early for that. Cause you know, every, everybody in the 1990s was like, oh, I could make pu money playing video games, which wasn't true back, which wasn't true back then, but that's right. You know, nowadays Scott Cunningham:You can that's right. Yeah. You know, that's right. You can do it. There's all kinds of ways you can make money doing things today that nobody knew was possible 10, 10 or 15 years ago. Even Kyle Kretschman:My Scott Cunningham:That's cool. Yeah. I, I, it's funny, you know, computer games can keep a, keep a kid in high school going, you know, like especially I think they're kind of misunderstood. I, I had a lot of friends that, well, I mean, I, I, I had, when I didn't have a lot of, we moved from a small town in Mississippi to Memphis and I, those, those that first year when I didn't have a friends, I did bulletin boards and played Sierra online games like Kings quest. And it's like, it's like, you know, not intertemporal smoothing, but like inner temporal socializing, smoothing, you know, so that you just kind of get through some periods that would otherwise be a little lonelier. Kyle Kretschman:Yeah, for sure. And I mean, I mean for this audience, like most video games are some sort of form of constrained optimization. So there was, there was the inkling that I, I liked understanding how economies worked in high school through this and yeah. Going back to my mom, my mom always said like she encouraged it and she encouraged education. And there was actually kind of like that nexus, whenever I took economics in high school, it was like, oh, you know, some of these games really are full economies that are constrained and constrained in a way that you can understand and complete in, you know, under a hundred hours. Right. But there was that combination that was kind of showing itself of computer science, computer gains and economics of putting itself together. Scott Cunningham:So you were kind of thinking even in high school about economics in that kind of like, you know, optimizing something and like, like almost that modern theory that we get in graduate school. Kyle Kretschman:I think more, I had the intuition when I didn't have know how to say what it was in high school because my high school was pretty forward and that it offered both advanced computer science courses that could get you through definitely through first year of undergrad, maybe even through second year with advanced placement. And then they also offered advanced placement economics. And so I, I ended up taking advanced place in economics my junior year when most people took senior year. And so whenever I was going small Scott Cunningham:Town, even in that small town, they had, you had good your high school. Good econ. Kyle Kretschman:Yeah. It was a real, it was a really good high school that would put together good curriculum that did a lot of college preparatory work though. They, wow. They really leaned into the advanced placement, the AP courses to get students ready to go to school. Scott Cunningham:Wow. Wow. So even at, as a junior, you're taking AP econ, you know, you don't have to take AP econ. That kind of is say that, that sounds like somebody that was kind of interested in it. Kyle Kretschman:Yeah, very much. Yeah. And again, as soon as I, I definitely didn't get to the graduate level of understanding, like, you know, LaGrange multipliers, but the, the micro and macro sequence just made intuitive sense to me. It was like, it was kind of where I was like, yeah, this fit. And this is how I think. And some people might criticize me now that I think too much like an economist. Right. Like, but at the same time, it just like, it started to put together that language and even more so some of the frameworks that really kind of drew me into it. Scott Cunningham:Well, did you, did you, did you notice that you had this interest in computer science and this interest in economics and that they might be one, did you get a feeling that they could be in conversation with each other? Kyle Kretschman:Not Scott Cunningham:At first, our ancestors a hundred years ago. Didn't, you know, those economists didn't think that way, but now it's just so natural for this generation of economists to be almost one half, you know, one third mathematician, one third economist, one third computer scientist. Kyle Kretschman:Yeah. So not at first, but I, I feel like I made have like lucked into it, honestly, because whenever I chose to go to Pitt, I chose to start as computer science because I knew what that pass was. I was inspired by my older brother, the great teacher in high school. And like, I was definitely like, okay, a software software development engineer career is great. It's cutting edge. It's there. But after probably like the first year, it just didn't feel that end state didn't feel right. And so I made kind of the hard decision to choose, honestly, to switch into economics as a major, because I wasn't sure what the end state would be, where I was going with it. Cuz it was definitely felt more amorphous, you know, it's a social science, so yeah. It didn't feel like it was gonna be as clear cut and as, and have as much certainty. But pretty quickly, like after a year was like, oh, well we're doing, we're using E views at the time. All right, this is coding. I know how to do this. This is great. Right. And starting, starting to see some of that in undergrad was like the, kind of the aha moment that like, yeah, this is, this is a place where I can apply this love of coding and problem solving, but problems and solutions that I find really, really hard and interesting. Scott Cunningham:It was because of econometrics though. It was in that. Kyle Kretschman:Exactly. Yeah, yeah. Scott Cunningham:Yeah. Wow. That's, that's really interesting because you know, I think it's still the case that, you know, you can easily end up with an econometrics class that remains purely theoretical and doesn't end up, you know, exposing the student with a lot of actual coding, but it sounds like your professors were, were getting you into working with data. Kyle Kretschman:That's correct. Yeah. Both. Both within the class. So like I said, we used E views at the time. Yeah. And again, kind of like learning as a go, I, I don't think I really knew what I was doing whenever we were typing commands and E views, but the computer scientist in me was like, okay, well this is a function. I know functions. Didn't put outputs, but definitely didn't understand necessarily things that were going under the hoods or you know, all of the theory that goes with it. Oh, right, right, right. So it was, you Scott Cunningham:Knew the coding part, you knew you were coding, but you did, but like the, the actual statistical modeling was kind of the new part, but that was a way for you to kind of engage it a little bit. Kyle Kretschman:Yep, exactly. Scott Cunningham:Oh, that's interesting. That's interesting. Well, so what were you gonna have to choose between a computer science and an econ major did or did you end up doing both? Kyle Kretschman:So I chose an econ major, but then I had what I would call basically minors or concentrations in computer science, but then also in statistics and also in math, because once, once I had an internship at a bank and was doing data entry and I was like, eh, I don't think this is what I wanna use my economics degree for. Yeah. I had a couple professors at pit named Steve Houston and Frank Giani who brought me on as a research assistant, an undergrad to start being part of some of like their survey projects and data collection. And even, even one of 'em I don't, Steve was crazy, but he even let me TA classes on undergrad, so oh, wow. But he kinda, I mean, I, I say that jokingly because it was formative for me, it was like, okay, this is great. How do I do more of this? And he was like, well, you go get your econ PhD. And I was like, so I can be a teacher with computer science and doing economics altogether. He goes, yeah, let's do that. And so it was with the help and support of some of these really good professors and education to kind push me on this path consider to get Ancon PhD. Scott Cunningham:Mm. And that's when you were like, so how, how, what, what year would you have been in your program? Kyle Kretschman:Probably. I think I was in my junior year where I was starting to explore this. And then in my senior year is where I was like, okay, I'm actually gonna be doing more more of this and applying to grad school because going back, as I said, I entered with some credits. So my senior year was very, I didn't need a full course load. So I was looking for other things to keep me busy, which maybe, maybe that's one of the themes of this conversation is I kinda kind of like the variety and really have variety seeking behavior too. Yeah, Scott Cunningham:Yeah, yeah. Yeah. So you graduate, was there like a field that you were mostly interested in? Kyle Kretschman:I thought I would be going into macro economics. Macro. Yep. Yeah, because Steve worked on the council of economic advisors and I was really inspired by that and the application of economics within, within policy and just again, always applied economics, not necessarily theoretical. So yeah. Then again was, that would be sort of like labor and macro was like the initial idea, but finally Scott, I didn't do all my homework and like, think about like what grad school looked like or all it looked like. I kind of went a little bit more naive than I think other people with, again, ideas of how I could become like a teacher, an educator with some of these tools versus like how disciplined and single thread you need to be on research to be within an econ PhD program and to see that. Scott Cunningham:So you, so you kind of were like, so when you were thinking about graduate schools, what, how, what, what did you sort of, can you walk me through like what you were thinking and how you went about trying to apply to graduate school and where you ultimately chose? Kyle Kretschman:Yeah, sure. So applied probably the, the top 10 and the top 10 probably said no thanks. But also then was targeting specific schools that we had relationships with that I knew would provide computer science and macros. So university at the Iowa at the time, this was 2000 and had a really strong macro program. And then also at the university of Texas with Dean Corbe there, they also had one in Russ Cooper. And so those were like the two that I was like targeting at outside of what the top schools were. But yeah, as I, I kind of mentioned, I, I might not have prepared myself well enough to be attractive for some of the most pop with top tier schools because kind of, you know, as I said, bounced around and would be yeah, a little bit working on it a little bit different things and have computer science versus being solely focused on like economics and math and things that might be more of what the top tier schools were looking for. Scott Cunningham:Yeah. Yeah. You know, you know, it's like the, I mean, I'm the same way. I didn't ha have any econ classes in college. I was a English major, but the, the, the diff there's so many students that sort of seem to almost for whatever reason, know a lot sooner what they want to do and then like make those choices. And then there's just many of us that are, you know, in a process of search yeah. That when you're in a process of search, well, you, you know, by definition, that's like you're using that time to search. Kyle Kretschman:That's exactly right. As Scott Cunningham:Opposed to saying, I've gotta take, I've gotta become a triple major computer science, math, econ, and have to do like, you know, these set of these set of steps that, you know, there's no way I could even have known to do it unless somebody had told me it's weird. I mean, it's just funny how the little things can have such big repercussions for your whole life, but it's, but it, it worked out great. So you end up, where do you end up going? Kyle Kretschman:I went to the university of Texas at Austin. Scott Cunningham:Yeah. Yeah. What year was that? And Kyle Kretschman:So, so this would've been 2002. Scott Cunningham:Oh, okay. So you go to oh 6 0 7. Kyle Kretschman:Okay. And so ended up working. So I ended up working a lot with Jason, Ava. Yeah. And who came in and became the, the head of the department. Yeah. Applied econometrician who just did an amazing job going back to whenever I said, I didn't know how things worked under the hood, in those formulas. He didn't even let us use those formulas. So anytime we were doing applied econometric econometrics with them, not only we learning to teach, we're learning the theory, but he said, you have to code it yourself. You have to do the matrix algebra, you have to calculate standard errors. You can't really call those functions. So that was probably again, that wasn't until the third year, but yeah, in the first year to go back a little bit, Scott Cunningham:I, that played to your strengths though. I bet that played to your strengths. Yeah. Just at the end of the day, wanting to be someone that, that wrote down the raw code. Kyle Kretschman:That's exactly right. And, but the first year I didn't play my strength. Yeah. Yeah. So the first year I felt, I felt a little bit outta water and I was like, this is, I remember when we were proving what local non association. And I was like, this is, this is one hard, but also like, again, going back to like, that is this actually how I wanna be spending my time and right. I, I was like, yes, I do. But I was like, I, I knew that I needed to get to those applied applications. Yeah. And so that's, again, why I was thankful to be able to work with Jason and Steve Trayo and a few other, they applied econometricians at Texas that really encouraged me to explore starting in the second year. They didn't us like pin it down. And so I, I thought I, at the second year I worked like wrote the first, a paper on school choice and trying to see if I could find some sort of instrument on school selection on public versus private. And again, so that led to like that idea of like applied econometrics was really, really the thing that like, I was like, okay, now this fits again. Once we got into second and third year Scott Cunningham:Was, was picking up that intuition, that kind of like labor style identification, causal inference kind of approach. Was that something you picked up from Jason or was that just like from your labor people? Oh, okay. Kyle Kretschman:Yeah. That's yeah. From Jason and Steve a lot. They did a great job of doing that. And yeah. So then, yeah. Then I, then I threw in, I knew threw a little bit of a switch in there also, and my co-author Nick master and Arti and closest friend and classmate in Texas was very theoretical and very interested in applied empirical IO. And so we started working in that field also together. And so then I got to work with the Han me vet and Ken Hendrix on using empirical IO. So, oh, wow. Yeah. And so again, Scott Cunningham:This is the more structural, more structural econometric. So you've got this like reduced, you've kind of got this like traditional labor reduced form type of, part of your brain. And then you've got this empirical IO structural part of your brain kind of emerging at the same time. Kyle Kretschman:That's right. That's exactly right. Yeah. And then we threw, we threw everybody for a loop. I also saying we wanted to study study politics and how money turns into vote using both using all these tools. So yeah, I can see here kind of saying in hindsight, like it all makes sense in this story that I'm telling you, but at the time it was more of what you were talking about. It was searching. It was, I wanna be working on really interesting applied problems. I love the toolkit that economics provides in framing. And yeah. I have to be coding to be able to utilize these tools that I've had built up in the past. Scott Cunningham:Yeah, yeah. Yeah. So, so matching with Nick was really important Kyle Kretschman:Very much. Scott Cunningham:And why, if you hadn't to match with Nick, I mean, just kind of outta curiosity, if you could articulate the value added of that whole partnership, what was it? Kyle Kretschman:Yes. Sure. So, so we matched basically from math camp going into, going into the first year because Nick came both from the pure math and physics background and also had some experience in the air force. So the air force was sending him to Texas and he, we were, we were definitely, we definitely didn't have a lot of vend overlap on the fact. He's like, well, I would have the intuition and some of the computer skills, Nick would have the theoretical math skills, Scott Cunningham:The theoretical math skills. Yep. Kyle Kretschman:And then we just had, we had the common factor that we wanted to work hard together and learn together and we're willing to, we're willing to intellectually hash out really tough things together. Yeah. So yeah, he huge credit to him through being able to put up with me. And he says, he says the same thing once in a while. But again, matching with somebody that had the, the more real analysis proof based understanding of math was so valuable for me. And especially, Scott Cunningham:I think some empirical IO, especially empirical IO, just being able to, you know, think like an economist in the area of IO is thinking real deep about, you know, a rich set of models and modeling approaches. Kyle Kretschman:That's Scott Cunningham:Exactly right. That's definitely not what you're learning in your econometrics classes, even though they might go together. Kyle Kretschman:Yep. So, so yeah, it was just a, it was a really good match from the beginning. And so we complimented each other and we're, we're able to build a strong enough relationship to be able to be able to hash out, have really long nights yelling at each other, we say in the office, but it never, it was always for educational purposes and lifting each other up. Scott Cunningham:Was that different than what you thought grad school was gonna be like? Kyle Kretschman:Yeah. So I knew the research component a little bit. I just didn't under understand the unstructured research on how that was gonna go and like the cadence and where it was gonna and how that was gonna be so required to develop your own viewpoint. Yeah. I thought it would be more directed cuz as a 22 year old, that was the experience I had generally. So that was the big one was the undirected and I liked it, but it was also very difficult. Scott Cunningham:How would you describe what you're talking about to your college self? Who kind of like, you know, he, he doesn't really, he doesn't even have the vocabulary for what you're describing. What would you say? It was like, Kyle Kretschman:I think you use a good term. You have to be not only wanting to search, you have to be willing to search, but you also, then you have to put in the guardrails yourself to keep it focused because you're not necessarily gonna have those external guardrails that you will have from an alternative path of going to either like a master's program that's gonna be more structured or going in an industry or going to get a job. Right. Like I mentioned at a bank for like a 22 year old where entry level jobs are gonna be more structured. Yeah. So yeah, I just, I, I probably knew it, but I didn't know what it meant to be and what, what it meant to experience it. Scott Cunningham:So how did Jason and, and Steve kind of, and any other faculty, how, how did they, how did they, I, so I did this interview with Susan athe and she was saying that, you know, the amazing thing that pat Maja did at Amazon was he managed to make economists productive, which kind it was kind of a weird, weird way of saying it. And so in a way it could, in a way you could imagine a department that sort of has like a, you know, this idea of like research has got to come. There's like a, there's like a, a journey that a graduate student has to come on to just to basically make a decision to be a researcher. Yeah. You know, and you could imagine that creating the conditions for that is, is involves faculty member, doing stuff that's not necessarily obvious. What, how did they, how do you think they contributed to that for you personally? Kyle Kretschman:For me personally, at the time, again, it goes back to encourage the exploration versus mandating or saying that I need to be on one path. So like even Nick and I at the time explore the idea of a private company and how, what, what that would be into like pinching, pitching a venture capitalist on, on that. So all those things, again, in grad school, they, they were encouraged, but they weren't structured at the time. Yeah. So yeah, I can, I can, I understand Susan's comment because I was, I was one of those economists who started pretty early with pat and we, we have a lot of good mechanisms that we've learned and built at Amazon when I was there at the time through pat, through lay other people who were willing to make the jump into this entrepreneurial space that hit the election and the, of coalesce of economists doing open book, empirical research, along with data science. Right. Just becoming more and more valuable and applicable, but is kind of what Susan piloting that we can, we can talk more about if you Scott Cunningham:Want. Yeah. I do wanna talk about that. I wanna talk about the, the decision though, you know, to, to be, because you, you sort of started off in college, you know, you said things like, oh, you can become an educator and then you've gone in this non-academic direction and you know, it, it, and that's like a, that's a more common story now, you know, right. Of, of top talent, very talented PhDs that you could have easily seen 20 years ago, would've been an academia. Their counterfactuals are, are following you. And so, you know, it's, it's a, it's a big part of our, you know, collective story as economists that this, this new labor market that didn't, that didn't exist historically now exists and draws in so much talent. And I was just curious in a way you're kind of like a, a first generation person like that, you know, when you think about it, right. Cause text's not very old, right. Facebook, Facebook, what it's like 2007. And so, you know, so you've got this, you, you, you've got this, this chance to kind of say like, it must have been, so I don't wanna put words in your mouth, but I guess I was just wondering, what were the feelings like as you considered not taking an academic track and when did it start to be something in your mind that you thought that's gonna be something I'm explore Kyle Kretschman:Probably pretty early, because if you wanna really trace the roots of like tech economists back, it starts obviously with Hal varying at Google and me and Nick, actually, we, we sent an email to Hal, probably 2008 saying, do you have any, have any use for some summer interns who can do some empirical IO? And he said, no, not, not at this time, but so, but he Scott Cunningham:Answered the email. Kyle Kretschman:He did answer the email. Yeah. It was nice, nice of him to answer. Cause we knew he was probably pretty busy, but so it, honestly, when Amazon started hiring economists, I was probably searching for about a year to move into tech. If you wanna move back to the decision point coming outta grad school, honestly it was a challenging labor or a challenging job market for me, somebody who is a lover variety, who is working on empirical IO problems with campaign, policy, campaign, finance reform, policy recognition. That's, that's not fitting a lot of the standard application process. Yeah. Once again, that's so that's probably a theme for me. And again, at the time it was hard. I was, I was in the running for jobs at VA wakes force that I thought would be really good fit because they're the EDU the emphasis would be on education with the research ability to do research and work on problems that were more widely probably policy oriented. Yeah. But neither neither of them came through. So I just always knew that I industry was gonna be an option. And so Scott Cunningham:What year is this? What, Kyle Kretschman:What, what this would've been in this would've been in Scott Cunningham:20 11, 20 11. Okay. Oh, so you moved through the, you moved through the program or kind of relatively quickly. Oh 7, 4, 4, 5 years. Okay. Kyle Kretschman:Five years. Yeah. Five years. Yeah. Oh six to 11. Okay. But so for about a year, about six. Yeah. Yeah. And so starting in 2013 is whenever I started applying to the first tech job as a data scientist and got it went great until I talked to the VP who was a business part, like pure business person. When I was talking to the hiring manager at the time, it was a company who was providing college counseling as a software service. And so they would do this at their, their clients were both for profit and not for profit companies. And we were talking like, we'd get into details about treatment effects models and how we could measure the impact of their intervention. It went great. But then I had the flyout scheduled, but then the interview with the VP, he said, well, how am I gonna monetize your algorithm? Right. And I was like, I'm not sure I know what algorithm means, but right. I, I wasn't prepared for that language and that application and how you turn econometric modeling and measurement into, into business impact at the time. Yes. Right. So spent another year looking around with different opportunities like that and honestly learning again. So, so whenever Amazon, so this would've been in 2014 and then Amazon was hiring its first big cohort with pat. So this was a cohort that was about, I think there was about 13 of us. It was a no brainer. Kyle Kretschman:Whenever, whenever we did the interview, it just was like, all right, this is exactly right for me. I was hop. I was hoping it was right on the other side. And I could probably tell you some funny stories about the interview process, but I was like, this is, this is what's meant to be. Yeah. So it, it, it was like a 10 year journey from 2004 when I switched outta computer science into 2014 being like this, just this fit. Scott Cunningham:Right. Right. Right. So outta curiosity, you know, is, is there, is there something that you think is supposed to be learned by the fact that when you were on the job market and you had that interview with that, that gig and the, and you get to the VP and he articulates questions that are not traditional econ questions, or even econometrics questions like business profitability to act, it's kind of ironic, isn't it like to everybody? That's not an economist. That's actually what we, they think we do, you know, is like, they think we do all that stuff. And then they don't know that we're like, like you said, you know, trying to set up a Lara and solve, solve it, like what's a Lara, but do you think your competition at that time did know how to answer questions like that? Like non-economists in those positions Kyle Kretschman:Probably at an inflection point. Yeah. Because this is the same time. Wherever machine learning is becoming more common toolkit with an industry. So there would be like machine learning algorithms that are designed for, you know, prediction, problem sequencing, anything like that that are specifically designed to be used in a business setting to monitor. Scott Cunningham:So they, they not only know machine learning, it's like, they also can kind of immediately articulate why this would be profitable. Kyle Kretschman:I think so. Yeah, because again, the computer, so it's like in learning the language and this is the language that would probably be more understood within a machine learning computer science version is okay, well, I'm gonna use this to change the recommendation engine right. Is very common one. Yeah. That's obviously gonna be, so how are you gonna monetize it? I'm gonna improve the match and the recommendation engine it's gonna have this. So I think at the time there was a little bit of it, but, you know, hopefully I think, I think I learned pretty quick that you can, you can use econometrics in a similar vein. As I said, it's a flavor of data science, Scott Cunningham:Have you had to become a blue collar machine learner? Kyle Kretschman:I've had to understand it, but not, I think you mean by blue collar, you mean like implementing it Scott Cunningham:And yeah, I just, when I, I usually say blue collar in the sense of like, you know, you, don't like, you know, you basically are picking up these skills, but you weren't like, you know, you didn't get a PhD in computer science. You know, Kyle Kretschman:The answer was then that answer is definitely yes. So like as we, as our cohort and as we grew, the economics discipline at Amazon, that was a big part of it is how one could we bring in some machine learning scientist help educate and teach us. Mm. And yeah. So, and even in, sometimes in lecture style, we would do that because it was so important, but then even more so learning to so that you can interact with different stakeholders specifically, like machine learning scientists. Mm. Then understanding when you can actually implement it and marry it within the econometric models was definitely a huge part of the education process. Scott Cunningham:So you go to Amazon, is that right? That's like your first entry into tech Kyle Kretschman:That's Scott Cunningham:Right. Is Amazon, what's your title? Kyle Kretschman:So Scott Scott Cunningham:A scientist or economist. Kyle Kretschman:I, it was something like business intelligence engineer. There wasn't an economist job family. There was, as you said, it was kinda the forefront. I think it was this. Yeah. I think that's what it was, but Scott Cunningham:Cause it is now right. Baja has a that's Kyle Kretschman:Right. Scott Cunningham:He created a job title called economist. Kyle Kretschman:That's right. Yeah. And that got set up about a year in, so like, and I was part of the group. So we would set these, we would set up like these people and process mechanisms that allow economists to be so influential and productive within Amazon. Scott Cunningham:Mm, okay. So how is he doing it? Why, why is Susan saying he performed a miracle by making economist productive? Can you kind of describe, like, if you had to just guess at like the counterfactual, if it hadn't been, you know, pat, it hadn't even been an economist that was hired into Pat's position. Like, what is it that he, what, what is it that he, or Amazon or whatever is making you go transform and become this new version of yourself? Kyle Kretschman:There's, there's a lot of factors and I could probably spend an hour on this, but I'll, I'll try to, I'll try to reduce it down to like some key mechanisms and ideas. The first is that Amazon is probably the most data driven company. I know. Mm. They are so focused on measurement, both of things you can directly measure. And, but they are. So they were very early interested in economic measurements that are UN observables either coming from like coming from econometric models. That, that was whenever pat demonstrated some of those that was like the light bulb went off the, so, because again, it, Amazon was run by and still generally is people with operation science background. And so this over index on measuring as, as coly and as precisely as possible, well that's that's economics. So that, that was part of it. Another part of it is culturally Amazon operates that makes decisions based on six page white papers, you wanna make some economists really productive, have them write a six page white paper instead of giving them a presentation, especially to people like who may be in the background with MBAs or other people who have a comparative advantage, we economists have a care advantage in writing. Kyle Kretschman:So it was little bit of like a surprise, but you might hear these anecdotes where it's true. Like whenever you go into a, a decision making meeting, you come in with your six page white paper that says here's the business decision to be made here is my recommendation. And here's why, and people sit there and it can be a room for five people can be a room of 25 executives. They sit and read the paper and they read the whole thing. Is there an append that can go on forever depending on how big the meeting is. Sure. But that structure of, of data driven decision making, combined with how you're presenting your argument is written seems like, seems like economists should be pretty good at that. Right? Scott Cunningham:Is that a pat thing? He came up with work, the work he made, Kyle Kretschman:What was the six page idea was from Jeff Bezos. And so that was, would Scott Cunningham:Those be circulated throughout the, throughout the, the, the firm, Kyle Kretschman:The stakeholders who needed to be part of the decision making they be circulated. But again, this is every, like everybody's writing six pages. PowerPoint is basically outlawed at, at Amazon. And again, that happened mid 2000. Sometimes people can Google it to find out, but that six page culture and decision making culture, just again, fit economists. Scott Cunningham:So how is a six page paper similar to the kinds of writing that, you know, you sort of associate with economists and how is it different? Kyle Kretschman:So its I'll start with the differences. So one with the six page versus like a 30 page academic, you are not going to be able to share the research process. You are not supposed to share the research process. You're supposed to share the clear recommendation and how you got to that recommendation. Right? So if you think about like a 30 page academic paper XT, be condensed down into those six pages. In my view, they're just, that's just not how the industry operates, but you probably would know better than me on that where, but so again, where it's the same is again, it's a data driven argument. The purpose of this paper, the abstract here is the hypothesis that I have that and here's how I tested it. And here's how I'm making my conclusion. So what I always found really honestly easy was I felt like I was doing the scientific process. Like I felt I, I was with business decision making it generally work within what is the hypothesis? How are we doing this? How are we testing it? What are we think some alternative conclusions could be, but what are we making towards it? So yeah, yeah. Again, it was closer to what I felt like would be a scientific paper in and that hold of day driven mindset is again, that's more, it's very common. Amazon have a common Spotify now Scott Cunningham:Has that been influential throughout, throughout industry? Has that, how have you noticed Amazon influencing Kyle Kretschman:Some Scott Cunningham:Yeah. Like most people don't understand. Kyle Kretschman:Yeah. There there's some companies who definitely have completely adopted it. There's some companies who haven't, but the, the six pager again, that's, this is not a, this isn't a concept just to economist and tech. This is the concept is, is held up as one of the key mechanisms for all of Amazon. Scott Cunningham:Mm mm Hmm. Kyle Kretschman:One other. Scott Cunningham:How often were you writing those? Kyle Kretschman:Depends on what level you were farther in my career. That's the only thing I did was write six page papers and it would be part of like, my team would help, but again, anytime you have a key business decision to be made or an update, like you're gonna be writing the six page. So yeah, it's again, the farther, the more seniority you have though, the more that becomes your job is to communicate side and guide through these business decisions. Scott Cunningham:Do they, to you, Kyle Kretschman:They belong to the team because it's always Scott Cunningham:Put 'em on a, you can't they're like proprietary though to Amazon. Kyle Kretschman:Oh, correct. Yeah. No, they, they're not publicly available. They're Scott Cunningham:Proprietary. Like it must is it what's that feel like to do something? What's it, what's it feel like to, to do something that creative in that kind of like scientific that's siloed within the firm? Does that feel strange? Kyle Kretschman:No, it didn't. Because what it enables is to be able to work on some of the hardest questions without having to worry about without having to worry about com communication strategies or right. For press release. So no, it felt like we were able, and this is going back to like some of the things that pat and we did at Amazon make successful. We worked on some of the hardest problems at Amazon from a very early stage because we said that it wouldn't be publicly available. Right. So that's gonna do that. And Scott Cunningham:That's been a key part. Yeah. Because okay. I get it. Okay. That, that makes a lot of sense. Yeah. So who did you discover? You were, go ahead. Sorry, Kyle. Kyle Kretschman:No, I was gonna say maybe the last me to highlight. Cause again, I, I, we could probably spend this whole interview on this, but the, the other key mechanism that pat pioneered was the proliferation of economists as a job family was not pat saying and us saying, go do this. And I can give through my own personal example. It was the other business executives, seeing the measurement, seeing the results on product, just saying, okay, I want that. So it really was a demand, AKA demand, internal demand for more economists, that was gonna say, I want this with my business decision making process and want these people who can do this and collaborate across the difference. It was not a, oh, we're gonna put economist in the siloed function that everybody's gonna come here. And that was, that was my story. But the very first year I worked on projects directly for the consumer CFO, basically the whole year. It wasn't necessarily by design, but it was what happened. And at the end of the year, year and a half, the, the VP of finance said, come over here and do this with me and come build, come build an economics team and an economics function here within my organization. And that's really is again, that's the real key was it was business decision makers, demanding the ability to understand this and demanding the skill set, just like they would data science, machine learning because of demonstrated value. Scott Cunningham:What were they witnessing with their own eyes that was so compelling that they would Inc that it would increase demand. Kyle Kretschman:So both I'll call it like ad hoc economic analysis on maybe big strategy projects, but also then the introduction of econometric systems into product. Scott Cunningham:Mm. What does that mean? Introduction of econometric systems into products. Kyle Kretschman:So say you have a product that is gonna, let's go back to the recommended system. And I use that again as an abstract, but within there you might make a change to it and you might make a change with the recommender system. That's gonna cause a treatment effect. Right. So, okay. So we can do that one off to estimate that, but you could also then build an economic system. That's gonna measure those treatment effects and changes like an AB platform or things like that. So maybe people might be more common and familiar with like experimental platforms. This would also be then econom. This would be sub out the AB part of it and sub in an economic model, that's going to be doing always on measurement sometimes at a, you know, service level. So sometimes within like individual pages, sometimes it's gonna be at a monthly level, but the integration of econometric models into the product. Scott Cunningham:Right, right. Wow. So how are you a different economist because of that experience at Amazon, if you had to guess, what was it the treatment effect? Kyle Kretschman:Oh, it mean it was, it was incredibly formative because it to tie like it put the fit together with the application to where I could understand and really to where it is, my job is to take a business question, turn it into a scientific process that can be solved with econometrics. And then also be thinking about, is this a problem that needs a scalable solution? Right. So, so Amazon taught me business integration taught me so many different languages, taught me leadership and management taught me how to work with stakeholders in collaborative ways, but then even more so how to deliver the value through econometric measurement, both again, as I said, not only, not only just in ad hoc research papers or one off analysis, but also then where does this fit directly within the products that we build in tech? Scott Cunningham:Yeah. So where'd you go, seems like people don't stay very long in tech. That's like normal. Whereas like, is, is that right? People kind of like, it, it's less normal to stay your whole career at Amazon unless is that wrong or, Kyle Kretschman:I mean, it's got it still do. So it's probably tough to say that because really the, the field started, like you said, really proliferated in 2012. So I stayed at Amazon for six years and I thought I'd be staying even longer. But Spotify came with the opportunity to one work on something I care very deeply about, which is the music industry. I'm a huge music fan. They also came with the idea to build again. So, you know, that was the part that really enticed me was Spotify did not have any PhD economists who were in an and, and economist roles. They had like one in a data science role, but they didn't have the structured economic discipline that they were seeing that Amazon was proliferating. And also then going into like Uber, Airbnb and the other tech companies. And so they said, can you build again? Kyle Kretschman:And I said, yeah, I'm, I'm excited to build. And then last one, all these there's definitely personal considerations here too. And Spotify just really did a great job showing how the company as a whole has Swedish cultures and values. And at the time I had a nine month old and they said, this is a great place to come be a father with the balance and that, and I said, all right, let's make the jump and come to Spotify. And so now I've been here about two years. So cuz I, I actually went to Spotify in may of 2020. Scott Cunningham:So remind me again, your job title at Spotify. Kyle Kretschman:So I'm head of economics. Scott Cunningham:Is, is that the, is that, is that like chief economist? I, I feel like I see different, different job titles and I don't know exactly what, what everything, Kyle Kretschman:Yeah. It, it it's on the path to it. So I'm, I'm the highest ranking PhD economist at Spotify. Scott Cunningham:I see. Okay. I've been there for two years. Okay, go ahead. Sorry. Kyle Kretschman:Yeah. Cause again, that's what I was brought into build was to build, like we did at Amazon was overall integration of PhD economists within the different business units. Scott Cunningham:So this is the part I'm, I'm having some hard time, like, you know, putting, visualizing or putting in my own words. What exactly will it look like if you have been successful in five years at that goal and what would it look like if you had been a complete, complete bust? What are the two things that are like empirical that I would be able to, to observe? Kyle Kretschman:Yeah. A complete bust is probably that an economics discipline is not, is not part of Spotify and there's not, there's not a job family. So a complete bus would've been, I, I moved to Spotify, an economics discipline. I either in, or I'm working data science job, what success looks like is actually what we put first from a, so I'll talk about the people in process, discipline success. We, I came into was Scott Cunningham:Real quick. So Kyle Kretschman:Foundation on basically. Yeah. Scott Cunningham:So, so failure actually would mean that the economist community within Spotify just never materialized, is that what you're saying? And that, and that means like this, having groups of economists that, that think and use the kinds of training we had in graduate school, but in a way that is actually productive in the firm is, is that, is that right? Kyle Kretschman:So, so yeah, and again, that's, Scott Cunningham:The job is successful if you're able to actually create internal demand for economists. Kyle Kretschman:Yep. That's right. And that's, that's what I would say against from the process side. And then from the product side, that's using econometric research in the ways that I've been talking about it's using it both not only for individual analysis, but also then building econometric measurement systems that improve the product to get towards Spotify's mission of, of billion listeners and fans who can connect with over a million creative artists who are making a living. So that's, so it's a combination, it's the combination people process. Do we have the people set up? Do we have this integrated system of economists working alongside all these different types of stakeholders along with the product side of, do we have these measurement techniques that we're applying in a way that is important to Spotify's not only Spotify's business, but all the stakeholders that have an interest in Bon life. Scott Cunningham:So I feel like, you know, I think to academics that, that, and, and maybe even to some degree students, maybe I'm, maybe I'm completely an outlier here and I'm wrong, but you know, I think there's this like really shallow is a negative word. It, I mean, shallow, literally more and just like, it's just the thinnest knowledge possible of what exactly, you know, the, the, the core skillset of a successful economist is in tech. You know, and for many people they think, I think they, they think it's such a primitive level. They're like, it needs to be somebody that can code, you know, it's a data scientist, but, but it, but it, but that's not what I associate with economics. Right. So what would you, what would you articulate? It is, Kyle Kretschman:So it's the ability to do econom applied econometric research. That's applied to business problems. Mm. So within that is coding. Yes. Scott Cunningham:Right, right. Within that is coding. Kyle Kretschman:I, the vast majority, I won't say everyone, but the vast majority of tech economists are gonna have some level of coding and maybe they're not coding anymore. Like I'm not doing any coding anymore, but like they, they have that ability. So that's just again, that's, that's a skillset, but the real ability is doing long-term economic research. Because the questions that we get asked are very hard and difficult, and they are maybe in the academic setting, maybe they are publication worthy, takes that take three years, four years to actually solve with the right model. Yeah. But it's the ability to take that three year research roadmap

In this week's episode of The Mixtape with Scott, I had the pleasure of interviewing Kyle Kretschman, Head of Economics at Spotify. It was a great opportunity for me because Kyle is one of the first economists I have spoken to who didn't enter tech as a senior economist (e.g., John List, Susan Athey, Michael Schwarz, Steve Tadelis). Kyle entered tech straight out of graduate school. He spent much of his career at Amazon, a firm that has more PhD economists than can be easily counted. Under Pat Bajari's leadership there, Kyle grew and his success was noticed such that he was then hired away by Spotify to lead up their economics team. At the end of the interview, I asked Kyle an economics article that has haunted his memories and he said “BLP”, which is affectionate shorthand that “Automobile Prices in Market Equilibrium” by Berry, Levinsohn and Pakes 1995 Econometrica goes by. I really enjoyed this interview, and despite the less than ideal sound quality at times, I hope you will too.But before I conclude, I wanted to share some more of my thoughts. This series I've been doing on “economists in tech”, which has included interviews with John List, Susan Athey, Michael Schwarz and Steve Tadelis, comes from a complex place inside me. First there is the sheer curiosity I have about it as a part of the labor market for PhD economists. As I have said before on here, the tech sector has exploded in the last decade and the demand for PhD economists has grown steadily year over year. Tech demand selects on PhD economists with promising academic style research inclinations. There is substantial positive selection in this market as firms seek out strong candidates can be produce value for them. This is reflected in both junior market salaries, but also senior. Job market candidates are economists with technical skills in econometrics and economic theory, not to mention possess competent computer programming skills in at least one but often several popular coding languages. They are also candidates who were often entertaining careers within academia at the time they entered tech, and in those academic careers, they envisioned themselves writing academic articles about research they found personally and scientifically important and meaningful. Going into tech, therefore, would at least seem to involve choice that may go far beyond merely that of taking one job over another. It may involve a choice between a career in academia and a career outside it, which for many of us can feel permanent, as though we are leaving academia. And for many economists, it may be the first time they have ever contemplated such a thing. If they do internalize the story that way, if they do see taking a job in tech as “leaving academia”, then I can imagine that for at least some economists, that may be complicated, at least. But there's another reason I have been wanting to talk to economists in tech and that is I am very concerned about the welfare of our PhD students. In a recent article published in the Journal of Economic Literature, economists interviewed graduate students in top economics programs. They found there incredibly high rates of depression, anxiety, loneliness and even suicidality. This is a common feature of graduate studies, but it is interesting that PhD economists have incredibly good employment opportunities and yet the depression and anxiety plague there too. One of the things that struck me in that study was the disconnect between what graduate students felt about their work and what their advisors felt about their own work. Many students, for instance, do not feel they are properly supported by advisers, do not believe their advisers care about their research success and do not even care about them as a person. Whereas most Americans (and faculty) feel that their work has a positive impact on society, only 20% of PhD students in economics feel that way. (I discussed the article as well as my own research on the mental health of PhD students here.) I suppose part of me feels a great sigh of relief to see the labor market for PhD economists expanding in light of those troubling statistics. If students know that life is full of infinite possibilities, then perhaps they can begin to process earlier what they want to do in the short years they have on this small spinning ball of rock we call Earth. If students do not in the end want to become professors, if they do not have the opportunities to become one, they should know that there is no “failure” involved there. Careers are just that — careers. They do not tell us who we are. The sooner a student can detach from the unhelpful story that our value is linked to a vita listing our accomplishments, the sooner they can begin their own life work of choosing their meaning. Can having more labor market opportunities with more employers competing for them help do that? Well no, not really. At least, not exactly. It can disrupt certain equilibrium, but then the new equilibrium can just as easily cover that up too. Still, I do like the idea that to keep students in academia, universities and departments must fight harder for them, pay attention to them, and invest in them as people. I like the idea that students have more options and that the options are diverse. Will it help their depression? Well, that's another matter, as that's complex. And presumably the economists in the survey I mentioned were themselves well aware of the career options they had since they were coming from the nation's top 10 PhD programs in economics. I suppose my point is that ultimately, the burden of life really cannot be resolved with money or career. We are trained to look there because we have boundless appetites. But ultimately the hard work of navigating life can only be helped so much by a job. We must still decide for ourselves what meaning we will choose for ourselves. But one thing I know, and one thing which I think our profession is profoundly bad at saying out loud, is that if we make our identity connected to vitas, we will not just be miserable, we will be hopeless, and probably poisoned. Such a mindset leads to endless laps on a brutalizing treadmill of meaningless performance in which a person chases for first place in a race they don't remember signing up for and which they cannot win. They compare themselves with others running, not knowing that they too are brutalized by their own treadmill, not realizing that it is impossible to catch up with someone else as there is always someone else ahead of us. The sooner we learn that the joy we long for will not come when we get a top 5, the sooner we can look elsewhere. It has taken me many years to relearn a lesson I learned decades ago — I am whole now. I am complete now. I still run, and I still chase, but I am not chasing completeness. I am not chasing my own wholeness. Being whole and complete has nothing to do with a career. Careers are ultimately orthogonal to hope, which does not mean they do not matter — they absolutely matter. But if asked to deliver meaning, we will find that our jobs are as weak as wet spaghetti at such a task as that.So, I suppose in some ways I simply want to announce — there are incredible opportunities for economists inside government, commerce and academia. But the weight of this life is not likely to be lighter in any one of them, for the weight we feel in life is largely self imposed, inside us, in the stories we tell about who we are and for many of us who we are not. Those stories are real, because we feel them and because we believe them, but they are not true. All stories are wrong, but some are useful, and the story that our lives can only matter if we have certain types of jobs or certain types of success, while it may be useful to getting a paper out or accomplishing something important, in a much bigger sense it is hollow at best and pure poison at worst. TRANSCRIPTThis transcript will be updated once the more complete transcript is finished; for now it was transcribed using voice-to-text machine learning.Kyle Kretschman:Might not have prepared myself well enough to be attractive for some of the most pop most top tier schools. Scott Cunningham:In this week's episode of the mix tape with Scott, I had the pleasure of interviewing Kyle kretchma the head of economics at the streaming platform. Spotify. Before I dive into the interview, though, I wanted to give you a bit of a heads up about the sound quality. Unfortunately, the sound quality in the interview on Kaza side is a bit muffled. We discussed refilming. It tried to find a way to tweak it, but there were certain constraints on the actual sound itself that kept us from being able to do it. And we didn't feel that refilming, it would be good because we thought that the interview had a lot of serendipitous kind of spontaneous tangents and things spoken about that. We thought students and people in academia would want to know, would need maybe even need to know. And I doubted that I could recreate it, cuz I don't even know why it happened. Scott Cunningham:So I'm gonna post a video version of this at my subs, for those who feel that a video version would help them kind of follow it in so far as the audio might be at times challenging. So check out the subst for those of you that wanna watch, watch it instead of just listen to it, hopefully that'll help. I won't say much here by way of introduction, except to say a few things about Kyle, because I wanted to let Kyle tell you his story in his own words, cuz it's his story to tell. And it's an interesting story. Kyle's a PhD economist though from the university of Texas Austin, which is down the road from where I live and work at Baylor, where he wrote on topics in graduate school and applied econometrics, empirical industrial organization or empirical IO and public choice after graduating, Kyle went to Amazon, not academia. Scott Cunningham:In fact, given we might start the boom of tech hiring PhD economists in the early to mid 20 2010s. You could say Kyle maybe was sort of one of the earlier hires among that second wave of PhD economists that went there. He worked for several years at Amazon before being hired away by Spotify to head up and lead a new economics team there, perhaps this is part of a broader trend of tech firms building up more internal teams, not just of data scientists, but like Amazon departments of economists who knows recall though from an earlier interview with Susan athe where, when I asked Susan why she said pat Maja had done something amazing at Amazon, she said he made economists productive. And in time he made many of them productive and very in productive from what I've been able to follow. And Kyle is from what I can gather someone whose skills matured and deepened under the leadership of Papa jar at Amazon and other leaders at and other economists at Amazon. Scott Cunningham:And he was ultimately hunted down by a major tech term to create an economics team there I'm by no means an expert on the labor market for PhD economists. I just have been very intrigued and curious by the, the, the Mar the labor market for PhD economists in tech, because well, partly because of realizing first that cause of inference was really valued in tech, but then to sort of realize that there was just this very large community of economists there, but I don't think it's controversial to say over the last 10 to 15 years, the tech industry really has been disruptive in the labor market for PhD economists. They continue to hire at the junior and senior market in larger and larger volume selecting more and more on people who likely would've gone into academia into tenure track or tenured positions. They pay very high wages, some of the very, some of the highest wages in the country, both at the junior level and especially at the, at the higher end at the, at the more advanced levels, people can earn compensation packages by the, in the, by the time they're in their thirties, that many of us didn't know were possible. Scott Cunningham:It's in my mind, historically novel, and I might be wrong about this, but it, it seems historically novel that the PhD economists who likely would've produced academic research papers in tenured and tenure track jobs have begun to branch out of academia, but maintain those skills and maintain that research output. It's partly driven best. I can tell, buy Amazon, I might be wrong, but by Amazon and paja, as well as Jeff Bezos own view, that economists are what I guess we would just say value added for many firms. Therefore I'm continuing to wanna speak with economists in tech to help better trace out the story. This interview with Kyle follows on the back of earlier interviews with people in tech like John list, you know, a, a distinguished professor of economics at the university of Chicago, but also the former chief economist that Lyft and Uber now Walmart Michael Schwartz, former professor of economics at Harvard. Now, chief economist at Microsoft and Susan athe former chief economist at Microsoft professor at Stanford and now chief economist at the DOJ. I hope you find this to be an interesting dive into the industry. Learn a little bit more about economists there, but by, by learning the about one particular important economist, there a, a young man named Kyle crutch, head of economics at Spotify, my name's Scott Cunningham. And this is the mix tape with Scott. Scott Cunningham:Well, it's my pleasure today to have, as my guest on the mix tape with Scott, Kyle crutch, Kyle, thanks so much for being on the call. Kyle Kretschman:Hey Scott, thanks for having me really appreciate the time to talk Scott Cunningham:Well before we get started with your career and, and everything. I was wondering if you could just tell us your name and your title and where you work. Kyle Kretschman:Sure. Yeah. As you said, I'm Kyle kretchma, I'm the head of economics at Spotify, Scott Cunningham:Head of economics at Spotify. Awesome. Okay. I can't wait to talk. So let me, let me, let's get started. I was wondering if you could just tell me where you grew up. Kyle Kretschman:Sure. So most of the time I grew up in outside of Pittsburgh, Pennsylvania, about an hour north of the city, real real small town probably had one stop light. And maybe the, the funny story that I can share is what I took my wife there. She asked where's the Starbucks. And I said, no Starbucks here. There's no Scott Cunningham:Starbucks. Kyle Kretschman:Yeah. So pretty small town called Chippewa township in Pennsylvania. Scott Cunningham:Oh, okay. Is that near like Amish stuff or anything like that? Kyle Kretschman:No, that's the other side of the state. So this would be Western Pennsylvania about near the end of the turnpike, about five minutes from the Ohio border. Scott Cunningham:Oh, okay. Okay. You said, but you, did you mention, you kind of grew up in different places? Kyle Kretschman:Yeah. So before that, my father worked in civil engineering and so would do build roads and bridges basically across every, across the nation. So I was actually born in Louisiana, lived there with, I think for a whole two, three weeks. I don't quite remember. Cause I was pretty young obviously, but then Michigan and then spent some time in Philadelphia before moving out to Pittsburgh around second grade. Scott Cunningham:Oh, that's kinda like, that's like when people described their parents being in the military, just kind of moving around a lot. Kyle Kretschman:Yeah. A little bit. So, but Scott Cunningham:Then you settled in the second grade Kyle Kretschman:That's right. Yeah. So outside of Pittsburgh and then stayed in Pittsburgh through high school and even through undergrad. Scott Cunningham:Oh, okay. Oh, you went to undergrad in Pennsylvania. Kyle Kretschman:Yeah, I did. So I went to undergrad at the university of Pittsburgh. Oh, okay. It was, yeah. If, I guess maybe continuing the story growing up in a town with no Starbucks. I was, I was pretty intrigued by going to a city. Yeah. And find out that lifestyle and yeah, we might have lived pretty close, like an hour away, but we didn't go down to the city very much. So Pittsburgh was just really, really enticing for a city to, for, to go to undergrad in. And so I basically looked at all schools that were in cities and so the proximity plus then the, the ability to just spread my wings and explore what it's like to be in a city was really, really enticing. Scott Cunningham:Did any of your friends go to pit with you? Kyle Kretschman:Yeah, so there's probably, I grew, I graduated from a class of about a little over 200 people in high school and I think there was like five or six people from high school that went to pit for my class. So definitely had some really good friends who went and kept in touch with, through undergrad. Scott Cunningham:Mm. Yeah. So it wasn't, were you sort of an early generation or you weren't, were you a first generation college student in your family or did your parents go to college Kyle Kretschman:Combination? So my dad went to Penn state civil engineer, as I mentioned, me and my mom actually graduated from undergrad the same week. So my mom went back to school later in life after me, after we went to school. And so yeah, we, we were able to celebrate graduation cuz she went to a small private school right outside of the city also. Scott Cunningham:Oh, okay. Okay. Yeah. Well, so what did you like to do in high school? Kyle Kretschman:So I played a lot of sports before high school and then I kind of switched into, and this was a traditional sports of football, basketball, baseball, but then I switched into tennis in high school. And so that kept me busy, but along with a lot of academics and really, really liked computer science. So played a lot of video games growing up, really enjoyed like that aspect in combination. Scott Cunningham:What games were your, were you, did you play on a, on a video game, plat platform? Like an Nintendo or did you play? Kyle Kretschman:Yeah, no, we played a lot of plays very much into like role playing games. Some of the arcade games like Marvel versus Capcom. So yeah. Yeah. Very, very interested in gaming. Yeah. Maybe I was a little too early for that. Cause you know, every, everybody in the 1990s was like, oh, I could make pu money playing video games, which wasn't true back, which wasn't true back then, but that's right. You know, nowadays Scott Cunningham:You can that's right. Yeah. You know, that's right. You can do it. There's all kinds of ways you can make money doing things today that nobody knew was possible 10, 10 or 15 years ago. Even Kyle Kretschman:My Scott Cunningham:That's cool. Yeah. I, I, it's funny, you know, computer games can keep a, keep a kid in high school going, you know, like especially I think they're kind of misunderstood. I, I had a lot of friends that, well, I mean, I, I, I had, when I didn't have a lot of, we moved from a small town in Mississippi to Memphis and I, those, those that first year when I didn't have a friends, I did bulletin boards and played Sierra online games like Kings quest. And it's like, it's like, you know, not intertemporal smoothing, but like inner temporal socializing, smoothing, you know, so that you just kind of get through some periods that would otherwise be a little lonelier. Kyle Kretschman:Yeah, for sure. And I mean, I mean for this audience, like most video games are some sort of form of constrained optimization. So there was, there was the inkling that I, I liked understanding how economies worked in high school through this and yeah. Going back to my mom, my mom always said like she encouraged it and she encouraged education. And there was actually kind of like that nexus, whenever I took economics in high school, it was like, oh, you know, some of these games really are full economies that are constrained and constrained in a way that you can understand and complete in, you know, under a hundred hours. Right. But there was that combination that was kind of showing itself of computer science, computer gains and economics of putting itself together. Scott Cunningham:So you were kind of thinking even in high school about economics in that kind of like, you know, optimizing something and like, like almost that modern theory that we get in graduate school. Kyle Kretschman:I think more, I had the intuition when I didn't have know how to say what it was in high school because my high school was pretty forward and that it offered both advanced computer science courses that could get you through definitely through first year of undergrad, maybe even through second year with advanced placement. And then they also offered advanced placement economics. And so I, I ended up taking advanced place in economics my junior year when most people took senior year. And so whenever I was going small Scott Cunningham:Town, even in that small town, they had, you had good your high school. Good econ. Kyle Kretschman:Yeah. It was a real, it was a really good high school that would put together good curriculum that did a lot of college preparatory work though. They, wow. They really leaned into the advanced placement, the AP courses to get students ready to go to school. Scott Cunningham:Wow. Wow. So even at, as a junior, you're taking AP econ, you know, you don't have to take AP econ. That kind of is say that, that sounds like somebody that was kind of interested in it. Kyle Kretschman:Yeah, very much. Yeah. And again, as soon as I, I definitely didn't get to the graduate level of understanding, like, you know, LaGrange multipliers, but the, the micro and macro sequence just made intuitive sense to me. It was like, it was kind of where I was like, yeah, this fit. And this is how I think. And some people might criticize me now that I think too much like an economist. Right. Like, but at the same time, it just like, it started to put together that language and even more so some of the frameworks that really kind of drew me into it. Scott Cunningham:Well, did you, did you, did you notice that you had this interest in computer science and this interest in economics and that they might be one, did you get a feeling that they could be in conversation with each other? Kyle Kretschman:Not Scott Cunningham:At first, our ancestors a hundred years ago. Didn't, you know, those economists didn't think that way, but now it's just so natural for this generation of economists to be almost one half, you know, one third mathematician, one third economist, one third computer scientist. Kyle Kretschman:Yeah. So not at first, but I, I feel like I made have like lucked into it, honestly, because whenever I chose to go to Pitt, I chose to start as computer science because I knew what that pass was. I was inspired by my older brother, the great teacher in high school. And like, I was definitely like, okay, a software software development engineer career is great. It's cutting edge. It's there. But after probably like the first year, it just didn't feel that end state didn't feel right. And so I made kind of the hard decision to choose, honestly, to switch into economics as a major, because I wasn't sure what the end state would be, where I was going with it. Cuz it was definitely felt more amorphous, you know, it's a social science, so yeah. It didn't feel like it was gonna be as clear cut and as, and have as much certainty. But pretty quickly, like after a year was like, oh, well we're doing, we're using E views at the time. All right, this is coding. I know how to do this. This is great. Right. And starting, starting to see some of that in undergrad was like the, kind of the aha moment that like, yeah, this is, this is a place where I can apply this love of coding and problem solving, but problems and solutions that I find really, really hard and interesting. Scott Cunningham:It was because of econometrics though. It was in that. Kyle Kretschman:Exactly. Yeah, yeah. Scott Cunningham:Yeah. Wow. That's, that's really interesting because you know, I think it's still the case that, you know, you can easily end up with an econometrics class that remains purely theoretical and doesn't end up, you know, exposing the student with a lot of actual coding, but it sounds like your professors were, were getting you into working with data. Kyle Kretschman:That's correct. Yeah. Both. Both within the class. So like I said, we used E views at the time. Yeah. And again, kind of like learning as a go, I, I don't think I really knew what I was doing whenever we were typing commands and E views, but the computer scientist in me was like, okay, well this is a function. I know functions. Didn't put outputs, but definitely didn't understand necessarily things that were going under the hoods or you know, all of the theory that goes with it. Oh, right, right, right. So it was, you Scott Cunningham:Knew the coding part, you knew you were coding, but you did, but like the, the actual statistical modeling was kind of the new part, but that was a way for you to kind of engage it a little bit. Kyle Kretschman:Yep, exactly. Scott Cunningham:Oh, that's interesting. That's interesting. Well, so what were you gonna have to choose between a computer science and an econ major did or did you end up doing both? Kyle Kretschman:So I chose an econ major, but then I had what I would call basically minors or concentrations in computer science, but then also in statistics and also in math, because once, once I had an internship at a bank and was doing data entry and I was like, eh, I don't think this is what I wanna use my economics degree for. Yeah. I had a couple professors at pit named Steve Houston and Frank Giani who brought me on as a research assistant, an undergrad to start being part of some of like their survey projects and data collection. And even, even one of 'em I don't, Steve was crazy, but he even let me TA classes on undergrad, so oh, wow. But he kinda, I mean, I, I say that jokingly because it was formative for me, it was like, okay, this is great. How do I do more of this? And he was like, well, you go get your econ PhD. And I was like, so I can be a teacher with computer science and doing economics altogether. He goes, yeah, let's do that. And so it was with the help and support of some of these really good professors and education to kind push me on this path consider to get Ancon PhD. Scott Cunningham:Mm. And that's when you were like, so how, how, what, what year would you have been in your program? Kyle Kretschman:Probably. I think I was in my junior year where I was starting to explore this. And then in my senior year is where I was like, okay, I'm actually gonna be doing more more of this and applying to grad school because going back, as I said, I entered with some credits. So my senior year was very, I didn't need a full course load. So I was looking for other things to keep me busy, which maybe, maybe that's one of the themes of this conversation is I kinda kind of like the variety and really have variety seeking behavior too. Yeah, Scott Cunningham:Yeah, yeah. Yeah. So you graduate, was there like a field that you were mostly interested in? Kyle Kretschman:I thought I would be going into macro economics. Macro. Yep. Yeah, because Steve worked on the council of economic advisors and I was really inspired by that and the application of economics within, within policy and just again, always applied economics, not necessarily theoretical. So yeah. Then again was, that would be sort of like labor and macro was like the initial idea, but finally Scott, I didn't do all my homework and like, think about like what grad school looked like or all it looked like. I kind of went a little bit more naive than I think other people with, again, ideas of how I could become like a teacher, an educator with some of these tools versus like how disciplined and single thread you need to be on research to be within an econ PhD program and to see that. Scott Cunningham:So you, so you kind of were like, so when you were thinking about graduate schools, what, how, what, what did you sort of, can you walk me through like what you were thinking and how you went about trying to apply to graduate school and where you ultimately chose? Kyle Kretschman:Yeah, sure. So applied probably the, the top 10 and the top 10 probably said no thanks. But also then was targeting specific schools that we had relationships with that I knew would provide computer science and macros. So university at the Iowa at the time, this was 2000 and had a really strong macro program. And then also at the university of Texas with Dean Corbe there, they also had one in Russ Cooper. And so those were like the two that I was like targeting at outside of what the top schools were. But yeah, as I, I kind of mentioned, I, I might not have prepared myself well enough to be attractive for some of the most pop with top tier schools because kind of, you know, as I said, bounced around and would be yeah, a little bit working on it a little bit different things and have computer science versus being solely focused on like economics and math and things that might be more of what the top tier schools were looking for. Scott Cunningham:Yeah. Yeah. You know, you know, it's like the, I mean, I'm the same way. I didn't ha have any econ classes in college. I was a English major, but the, the, the diff there's so many students that sort of seem to almost for whatever reason, know a lot sooner what they want to do and then like make those choices. And then there's just many of us that are, you know, in a process of search yeah. That when you're in a process of search, well, you, you know, by definition, that's like you're using that time to search. Kyle Kretschman:That's exactly right. As Scott Cunningham:Opposed to saying, I've gotta take, I've gotta become a triple major computer science, math, econ, and have to do like, you know, these set of these set of steps that, you know, there's no way I could even have known to do it unless somebody had told me it's weird. I mean, it's just funny how the little things can have such big repercussions for your whole life, but it's, but it, it worked out great. So you end up, where do you end up going? Kyle Kretschman:I went to the university of Texas at Austin. Scott Cunningham:Yeah. Yeah. What year was that? And Kyle Kretschman:So, so this would've been 2002. Scott Cunningham:Oh, okay. So you go to oh 6 0 7. Kyle Kretschman:Okay. And so ended up working. So I ended up working a lot with Jason, Ava. Yeah. And who came in and became the, the head of the department. Yeah. Applied econometrician who just did an amazing job going back to whenever I said, I didn't know how things worked under the hood, in those formulas. He didn't even let us use those formulas. So anytime we were doing applied econometric econometrics with them, not only we learning to teach, we're learning the theory, but he said, you have to code it yourself. You have to do the matrix algebra, you have to calculate standard errors. You can't really call those functions. So that was probably again, that wasn't until the third year, but yeah, in the first year to go back a little bit, Scott Cunningham:I, that played to your strengths though. I bet that played to your strengths. Yeah. Just at the end of the day, wanting to be someone that, that wrote down the raw code. Kyle Kretschman:That's exactly right. And, but the first year I didn't play my strength. Yeah. Yeah. So the first year I felt, I felt a little bit outta water and I was like, this is, I remember when we were proving what local non association. And I was like, this is, this is one hard, but also like, again, going back to like, that is this actually how I wanna be spending my time and right. I, I was like, yes, I do. But I was like, I, I knew that I needed to get to those applied applications. Yeah. And so that's, again, why I was thankful to be able to work with Jason and Steve Trayo and a few other, they applied econometricians at Texas that really encouraged me to explore starting in the second year. They didn't us like pin it down. And so I, I thought I, at the second year I worked like wrote the first, a paper on school choice and trying to see if I could find some sort of instrument on school selection on public versus private. And again, so that led to like that idea of like applied econometrics was really, really the thing that like, I was like, okay, now this fits again. Once we got into second and third year Scott Cunningham:Was, was picking up that intuition, that kind of like labor style identification, causal inference kind of approach. Was that something you picked up from Jason or was that just like from your labor people? Oh, okay. Kyle Kretschman:Yeah. That's yeah. From Jason and Steve a lot. They did a great job of doing that. And yeah. So then, yeah. Then I, then I threw in, I knew threw a little bit of a switch in there also, and my co-author Nick master and Arti and closest friend and classmate in Texas was very theoretical and very interested in applied empirical IO. And so we started working in that field also together. And so then I got to work with the Han me vet and Ken Hendrix on using empirical IO. So, oh, wow. Yeah. And so again, Scott Cunningham:This is the more structural, more structural econometric. So you've got this like reduced, you've kind of got this like traditional labor reduced form type of, part of your brain. And then you've got this empirical IO structural part of your brain kind of emerging at the same time. Kyle Kretschman:That's right. That's exactly right. Yeah. And then we threw, we threw everybody for a loop. I also saying we wanted to study study politics and how money turns into vote using both using all these tools. So yeah, I can see here kind of saying in hindsight, like it all makes sense in this story that I'm telling you, but at the time it was more of what you were talking about. It was searching. It was, I wanna be working on really interesting applied problems. I love the toolkit that economics provides in framing. And yeah. I have to be coding to be able to utilize these tools that I've had built up in the past. Scott Cunningham:Yeah, yeah. Yeah. So, so matching with Nick was really important Kyle Kretschman:Very much. Scott Cunningham:And why, if you hadn't to match with Nick, I mean, just kind of outta curiosity, if you could articulate the value added of that whole partnership, what was it? Kyle Kretschman:Yes. Sure. So, so we matched basically from math camp going into, going into the first year because Nick came both from the pure math and physics background and also had some experience in the air force. So the air force was sending him to Texas and he, we were, we were definitely, we definitely didn't have a lot of vend overlap on the fact. He's like, well, I would have the intuition and some of the computer skills, Nick would have the theoretical math skills, Scott Cunningham:The theoretical math skills. Yep. Kyle Kretschman:And then we just had, we had the common factor that we wanted to work hard together and learn together and we're willing to, we're willing to intellectually hash out really tough things together. Yeah. So yeah, he huge credit to him through being able to put up with me. And he says, he says the same thing once in a while. But again, matching with somebody that had the, the more real analysis proof based understanding of math was so valuable for me. And especially, Scott Cunningham:I think some empirical IO, especially empirical IO, just being able to, you know, think like an economist in the area of IO is thinking real deep about, you know, a rich set of models and modeling approaches. Kyle Kretschman:That's Scott Cunningham:Exactly right. That's definitely not what you're learning in your econometrics classes, even though they might go together. Kyle Kretschman:Yep. So, so yeah, it was just a, it was a really good match from the beginning. And so we complimented each other and we're, we're able to build a strong enough relationship to be able to be able to hash out, have really long nights yelling at each other, we say in the office, but it never, it was always for educational purposes and lifting each other up. Scott Cunningham:Was that different than what you thought grad school was gonna be like? Kyle Kretschman:Yeah. So I knew the research component a little bit. I just didn't under understand the unstructured research on how that was gonna go and like the cadence and where it was gonna and how that was gonna be so required to develop your own viewpoint. Yeah. I thought it would be more directed cuz as a 22 year old, that was the experience I had generally. So that was the big one was the undirected and I liked it, but it was also very difficult. Scott Cunningham:How would you describe what you're talking about to your college self? Who kind of like, you know, he, he doesn't really, he doesn't even have the vocabulary for what you're describing. What would you say? It was like, Kyle Kretschman:I think you use a good term. You have to be not only wanting to search, you have to be willing to search, but you also, then you have to put in the guardrails yourself to keep it focused because you're not necessarily gonna have those external guardrails that you will have from an alternative path of going to either like a master's program that's gonna be more structured or going in an industry or going to get a job. Right. Like I mentioned at a bank for like a 22 year old where entry level jobs are gonna be more structured. Yeah. So yeah, I just, I, I probably knew it, but I didn't know what it meant to be and what, what it meant to experience it. Scott Cunningham:So how did Jason and, and Steve kind of, and any other faculty, how, how did they, how did they, I, so I did this interview with Susan athe and she was saying that, you know, the amazing thing that pat Maja did at Amazon was he managed to make economists productive, which kind it was kind of a weird, weird way of saying it. And so in a way it could, in a way you could imagine a department that sort of has like a, you know, this idea of like research has got to come. There's like a, there's like a, a journey that a graduate student has to come on to just to basically make a decision to be a researcher. Yeah. You know, and you could imagine that creating the conditions for that is, is involves faculty member, doing stuff that's not necessarily obvious. What, how did they, how do you think they contributed to that for you personally? Kyle Kretschman:For me personally, at the time, again, it goes back to encourage the exploration versus mandating or saying that I need to be on one path. So like even Nick and I at the time explore the idea of a private company and how, what, what that would be into like pinching, pitching a venture capitalist on, on that. So all those things, again, in grad school, they, they were encouraged, but they weren't structured at the time. Yeah. So yeah, I can, I can, I understand Susan's comment because I was, I was one of those economists who started pretty early with pat and we, we have a lot of good mechanisms that we've learned and built at Amazon when I was there at the time through pat, through lay other people who were willing to make the jump into this entrepreneurial space that hit the election and the, of coalesce of economists doing open book, empirical research, along with data science. Right. Just becoming more and more valuable and applicable, but is kind of what Susan piloting that we can, we can talk more about if you Scott Cunningham:Want. Yeah. I do wanna talk about that. I wanna talk about the, the decision though, you know, to, to be, because you, you sort of started off in college, you know, you said things like, oh, you can become an educator and then you've gone in this non-academic direction and you know, it, it, and that's like a, that's a more common story now, you know, right. Of, of top talent, very talented PhDs that you could have easily seen 20 years ago, would've been an academia. Their counterfactuals are, are following you. And so, you know, it's, it's a, it's a big part of our, you know, collective story as economists that this, this new labor market that didn't, that didn't exist historically now exists and draws in so much talent. And I was just curious in a way you're kind of like a, a first generation person like that, you know, when you think about it, right. Cause text's not very old, right. Facebook, Facebook, what it's like 2007. And so, you know, so you've got this, you, you, you've got this, this chance to kind of say like, it must have been, so I don't wanna put words in your mouth, but I guess I was just wondering, what were the feelings like as you considered not taking an academic track and when did it start to be something in your mind that you thought that's gonna be something I'm explore Kyle Kretschman:Probably pretty early, because if you wanna really trace the roots of like tech economists back, it starts obviously with Hal varying at Google and me and Nick, actually, we, we sent an email to Hal, probably 2008 saying, do you have any, have any use for some summer interns who can do some empirical IO? And he said, no, not, not at this time, but so, but he Scott Cunningham:Answered the email. Kyle Kretschman:He did answer the email. Yeah. It was nice, nice of him to answer. Cause we knew he was probably pretty busy, but so it, honestly, when Amazon started hiring economists, I was probably searching for about a year to move into tech. If you wanna move back to the decision point coming outta grad school, honestly it was a challenging labor or a challenging job market for me, somebody who is a lover variety, who is working on empirical IO problems with campaign, policy, campaign, finance reform, policy recognition. That's, that's not fitting a lot of the standard application process. Yeah. Once again, that's so that's probably a theme for me. And again, at the time it was hard. I was, I was in the running for jobs at VA wakes force that I thought would be really good fit because they're the EDU the emphasis would be on education with the research ability to do research and work on problems that were more widely probably policy oriented. Yeah. But neither neither of them came through. So I just always knew that I industry was gonna be an option. And so Scott Cunningham:What year is this? What, Kyle Kretschman:What, what this would've been in this would've been in Scott Cunningham:20 11, 20 11. Okay. Oh, so you moved through the, you moved through the program or kind of relatively quickly. Oh 7, 4, 4, 5 years. Okay. Kyle Kretschman:Five years. Yeah. Five years. Yeah. Oh six to 11. Okay. But so for about a year, about six. Yeah. Yeah. And so starting in 2013 is whenever I started applying to the first tech job as a data scientist and got it went great until I talked to the VP who was a business part, like pure business person. When I was talking to the hiring manager at the time, it was a company who was providing college counseling as a software service. And so they would do this at their, their clients were both for profit and not for profit companies. And we were talking like, we'd get into details about treatment effects models and how we could measure the impact of their intervention. It went great. But then I had the flyout scheduled, but then the interview with the VP, he said, well, how am I gonna monetize your algorithm? Right. And I was like, I'm not sure I know what algorithm means, but right. I, I wasn't prepared for that language and that application and how you turn econometric modeling and measurement into, into business impact at the time. Yes. Right. So spent another year looking around with different opportunities like that and honestly learning again. So, so whenever Amazon, so this would've been in 2014 and then Amazon was hiring its first big cohort with pat. So this was a cohort that was about, I think there was about 13 of us. It was a no brainer. Kyle Kretschman:Whenever, whenever we did the interview, it just was like, all right, this is exactly right for me. I was hop. I was hoping it was right on the other side. And I could probably tell you some funny stories about the interview process, but I was like, this is, this is what's meant to be. Yeah. So it, it, it was like a 10 year journey from 2004 when I switched outta computer science into 2014 being like this, just this fit. Scott Cunningham:Right. Right. Right. So outta curiosity, you know, is, is there, is there something that you think is supposed to be learned by the fact that when you were on the job market and you had that interview with that, that gig and the, and you get to the VP and he articulates questions that are not traditional econ questions, or even econometrics questions like business profitability to act, it's kind of ironic, isn't it like to everybody? That's not an economist. That's actually what we, they think we do, you know, is like, they think we do all that stuff. And then they don't know that we're like, like you said, you know, trying to set up a Lara and solve, solve it, like what's a Lara, but do you think your competition at that time did know how to answer questions like that? Like non-economists in those positions Kyle Kretschman:Probably at an inflection point. Yeah. Because this is the same time. Wherever machine learning is becoming more common toolkit with an industry. So there would be like machine learning algorithms that are designed for, you know, prediction, problem sequencing, anything like that that are specifically designed to be used in a business setting to monitor. Scott Cunningham:So they, they not only know machine learning, it's like, they also can kind of immediately articulate why this would be profitable. Kyle Kretschman:I think so. Yeah, because again, the computer, so it's like in learning the language and this is the language that would probably be more understood within a machine learning computer science version is okay, well, I'm gonna use this to change the recommendation engine right. Is very common one. Yeah. That's obviously gonna be, so how are you gonna monetize it? I'm gonna improve the match and the recommendation engine it's gonna have this. So I think at the time there was a little bit of it, but, you know, hopefully I think, I think I learned pretty quick that you can, you can use econometrics in a similar vein. As I said, it's a flavor of data science, Scott Cunningham:Have you had to become a blue collar machine learner? Kyle Kretschman:I've had to understand it, but not, I think you mean by blue collar, you mean like implementing it Scott Cunningham:And yeah, I just, when I, I usually say blue collar in the sense of like, you know, you, don't like, you know, you basically are picking up these skills, but you weren't like, you know, you didn't get a PhD in computer science. You know, Kyle Kretschman:The answer was then that answer is definitely yes. So like as we, as our cohort and as we grew, the economics discipline at Amazon, that was a big part of it is how one could we bring in some machine learning scientist help educate and teach us. Mm. And yeah. So, and even in, sometimes in lecture style, we would do that because it was so important, but then even more so learning to so that you can interact with different stakeholders specifically, like machine learning scientists. Mm. Then understanding when you can actually implement it and marry it within the econometric models was definitely a huge part of the education process. Scott Cunningham:So you go to Amazon, is that right? That's like your first entry into tech Kyle Kretschman:That's Scott Cunningham:Right. Is Amazon, what's your title? Kyle Kretschman:So Scott Scott Cunningham:A scientist or economist. Kyle Kretschman:I, it was something like business intelligence engineer. There wasn't an economist job family. There was, as you said, it was kinda the forefront. I think it was this. Yeah. I think that's what it was, but Scott Cunningham:Cause it is now right. Baja has a that's Kyle Kretschman:Right. Scott Cunningham:He created a job title called economist. Kyle Kretschman:That's right. Yeah. And that got set up about a year in, so like, and I was part of the group. So we would set these, we would set up like these people and process mechanisms that allow economists to be so influential and productive within Amazon. Scott Cunningham:Mm, okay. So how is he doing it? Why, why is Susan saying he performed a miracle by making economist productive? Can you kind of describe, like, if you had to just guess at like the counterfactual, if it hadn't been, you know, pat, it hadn't even been an economist that was hired into Pat's position. Like, what is it that he, what, what is it that he, or Amazon or whatever is making you go transform and become this new version of yourself? Kyle Kretschman:There's, there's a lot of factors and I could probably spend an hour on this, but I'll, I'll try to, I'll try to reduce it down to like some key mechanisms and ideas. The first is that Amazon is probably the most data driven company. I know. Mm. They are so focused on measurement, both of things you can directly measure. And, but they are. So they were very early interested in economic measurements that are UN observables either coming from like coming from econometric models. That, that was whenever pat demonstrated some of those that was like the light bulb went off the, so, because again, it, Amazon was run by and still generally is people with operation science background. And so this over index on measuring as, as coly and as precisely as possible, well that's that's economics. So that, that was part of it. Another part of it is culturally Amazon operates that makes decisions based on six page white papers, you wanna make some economists really productive, have them write a six page white paper instead of giving them a presentation, especially to people like who may be in the background with MBAs or other people who have a comparative advantage, we economists have a care advantage in writing. Kyle Kretschman:So it was little bit of like a surprise, but you might hear these anecdotes where it's true. Like whenever you go into a, a decision making meeting, you come in with your six page white paper that says here's the business decision to be made here is my recommendation. And here's why, and people sit there and it can be a room for five people can be a room of 25 executives. They sit and read the paper and they read the whole thing. Is there an append that can go on forever depending on how big the meeting is. Sure. But that structure of, of data driven decision making, combined with how you're presenting your argument is written seems like, seems like economists should be pretty good at that. Right? Scott Cunningham:Is that a pat thing? He came up with work, the work he made, Kyle Kretschman:What was the six page idea was from Jeff Bezos. And so that was, would Scott Cunningham:Those be circulated throughout the, throughout the, the, the firm, Kyle Kretschman:The stakeholders who needed to be part of the decision making they be circulated. But again, this is every, like everybody's writing six pages. PowerPoint is basically outlawed at, at Amazon. And again, that happened mid 2000. Sometimes people can Google it to find out, but that six page culture and decision making culture, just again, fit economists. Scott Cunningham:So how is a six page paper similar to the kinds of writing that, you know, you sort of associate with economists and how is it different? Kyle Kretschman:So its I'll start with the differences. So one with the six page versus like a 30 page academic, you are not going to be able to share the research process. You are not supposed to share the research process. You're supposed to share the clear recommendation and how you got to that recommendation. Right? So if you think about like a 30 page academic paper XT, be condensed down into those six pages. In my view, they're just, that's just not how the industry operates, but you probably would know better than me on that where, but so again, where it's the same is again, it's a data driven argument. The purpose of this paper, the abstract here is the hypothesis that I have that and here's how I tested it. And here's how I'm making my conclusion. So what I always found really honestly easy was I felt like I was doing the scientific process. Like I felt I, I was with business decision making it generally work within what is the hypothesis? How are we doing this? How are we testing it? What are we think some alternative conclusions could be, but what are we making towards it? So yeah, yeah. Again, it was closer to what I felt like would be a scientific paper in and that hold of day driven mindset is again, that's more, it's very common. Amazon have a common Spotify now Scott Cunningham:Has that been influential throughout, throughout industry? Has that, how have you noticed Amazon influencing Kyle Kretschman:Some Scott Cunningham:Yeah. Like most people don't understand. Kyle Kretschman:Yeah. There there's some companies who definitely have completely adopted it. There's some companies who haven't, but the, the six pager again, that's, this is not a, this isn't a concept just to economist and tech. This is the concept is, is held up as one of the key mechanisms for all of Amazon. Scott Cunningham:Mm mm Hmm. Kyle Kretschman:One other. Scott Cunningham:How often were you writing those? Kyle Kretschman:Depends on what level you were farther in my career. That's the only thing I did was write six page papers and it would be part of like, my team would help, but again, anytime you have a key business decision to be made or an update, like you're gonna be writing the six page. So yeah, it's again, the farther, the more seniority you have though, the more that becomes your job is to communicate side and guide through these business decisions. Scott Cunningham:Do they, to you, Kyle Kretschman:They belong to the team because it's always Scott Cunningham:Put 'em on a, you can't they're like proprietary though to Amazon. Kyle Kretschman:Oh, correct. Yeah. No, they, they're not publicly available. They're Scott Cunningham:Proprietary. Like it must is it what's that feel like to do something? What's it, what's it feel like to, to do something that creative in that kind of like scientific that's siloed within the firm? Does that feel strange? Kyle Kretschman:No, it didn't. Because what it enables is to be able to work on some of the hardest questions without having to worry about without having to worry about com communication strategies or right. For press release. So no, it felt like we were able, and this is going back to like some of the things that pat and we did at Amazon make successful. We worked on some of the hardest problems at Amazon from a very early stage because we said that it wouldn't be publicly available. Right. So that's gonna do that. And Scott Cunningham:That's been a key part. Yeah. Because okay. I get it. Okay. That, that makes a lot of sense. Yeah. So who did you discover? You were, go ahead. Sorry, Kyle. Kyle Kretschman:No, I was gonna say maybe the last me to highlight. Cause again, I, I, we could probably spend this whole interview on this, but the, the other key mechanism that pat pioneered was the proliferation of economists as a job family was not pat saying and us saying, go do this. And I can give through my own personal example. It was the other business executives, seeing the measurement, seeing the results on product, just saying, okay, I want that. So it really was a demand, AKA demand, internal demand for more economists, that was gonna say, I want this with my business decision making process and want these people who can do this and collaborate across the difference. It was not a, oh, we're gonna put economist in the siloed function that everybody's gonna come here. And that was, that was my story. But the very first year I worked on projects directly for the consumer CFO, basically the whole year. It wasn't necessarily by design, but it was what happened. And at the end of the year, year and a half, the, the VP of finance said, come over here and do this with me and come build, come build an economics team and an economics function here within my organization. And that's really is again, that's the real key was it was business decision makers, demanding the ability to understand this and demanding the skill set, just like they would data science, machine learning because of demonstrated value. Scott Cunningham:What were they witnessing with their own eyes that was so compelling that they would Inc that it would increase demand. Kyle Kretschman:So both I'll call it like ad hoc economic analysis on maybe big strategy projects, but also then the introduction of econometric systems into product. Scott Cunningham:Mm. What does that mean? Introduction of econometric systems into products. Kyle Kretschman:So say you have a product that is gonna, let's go back to the recommended system. And I use that again as an abstract, but within there you might make a change to it and you might make a change with the recommender system. That's gonna cause a treatment effect. Right. So, okay. So we can do that one off to estimate that, but you could also then build an economic system. That's gonna measure those treatment effects and changes like an AB platform or things like that. So maybe people might be more common and familiar with like experimental platforms. This would also be then econom. This would be sub out the AB part of it and sub in an economic model, that's going to be doing always on measurement sometimes at a, you know, service level. So sometimes within like individual pages, sometimes it's gonna be at a monthly level, but the integration of econometric models into the product. Scott Cunningham:Right, right. Wow. So how are you a different economist because of that experience at Amazon, if you had to guess, what was it the treatment effect? Kyle Kretschman:Oh, it mean it was, it was incredibly formative because it to tie like it put the fit together with the application to where I could understand and really to where it is, my job is to take a business question, turn it into a scientific process that can be solved with econometrics. And then also be thinking about, is this a problem that needs a scalable solution? Right. So, so Amazon taught me business integration taught me so many different languages, taught me leadership and management taught me how to work with stakeholders in collaborative ways, but then even more so how to deliver the value through econometric measurement, both again, as I said, not only, not only just in ad hoc research papers or one off analysis, but also then where does this fit directly within the products that we build in tech? Scott Cunningham:Yeah. So where'd you go, seems like people don't stay very long in tech. That's like normal. Whereas like, is, is that right? People kind of like, it, it's less normal to stay your whole career at Amazon unless is that wrong or, Kyle Kretschman:I mean, it's got it still do. So it's probably tough to say that because really the, the field started, like you said, really proliferated in 2012. So I stayed at Amazon for six years and I thought I'd be staying even longer. But Spotify came with the opportunity to one work on something I care very deeply about, which is the music industry. I'm a huge music fan. They also came with the idea to build again. So, you know, that was the part that really enticed me was Spotify did not have any PhD economists who were in an and, and economist roles. They had like one in a data science role, but they didn't have the structured economic discipline that they were seeing that Amazon was proliferating. And also then going into like Uber, Airbnb and the other tech companies. And so they said, can you build again? Kyle Kretschman:And I said, yeah, I'm, I'm excited to build. And then last one, all these there's definitely personal considerations here too. And Spotify just really did a great job showing how the company as a whole has Swedish cultures and values. And at the time I had a nine month old and they said, this is a great place to come be a father with the balance and that, and I said, all right, let's make the jump and come to Spotify. And so now I've been here about two years. So cuz I, I actually went to Spotify in may of 2020. Scott Cunningham:So remind me again, your job title at Spotify. Kyle Kretschman:So I'm head of economics. Scott Cunningham:Is, is that the, is that, is that like chief economist? I, I feel like I see different, different job titles and I don't know exactly what, what everything, Kyle Kretschman:Yeah. It, it it's on the path to it. So I'm, I'm the highest ranking PhD economist at Spotify. Scott Cunningham:I see. Okay. I've been there for two years. Okay, go ahead. Sorry. Kyle Kretschman:Yeah. Cause again, that's what I was brought into build was to build, like we did at Amazon was overall integration of PhD economists within the different business units. Scott Cunningham:So this is the part I'm, I'm having some hard time, like, you know, putting, visualizing or putting in my own words. What exactly will it look like if you have been successful in five years at that goal and what would it look like if you had been a complete, complete bust? What are the two things that are like empirical that I would be able to, to observe? Kyle Kretschman:Yeah. A complete bust is probably that an economics discipline is not, is not part of Spotify and there's not, there's not a job family. So a complete bus would've been, I, I moved to Spotify, an economics discipline. I either in, or I'm working data science job, what success looks like is actually what we put first from a, so I'll talk about the people in process, discipline success. We, I came into was Scott Cunningham:Real quick. So Kyle Kretschman:Foundation on basically. Yeah. Scott Cunningham:So, so failure actually would mean that the economist community within Spotify just never materialized, is that what you're saying? And that, and that means like this, having groups of economists that, that think and use the kinds of training we had in graduate school, but in a way that is actually productive in the firm is, is that, is that right? Kyle Kretschman:So, so yeah, and again, that's, Scott Cunningham:The job is successful if you're able to actually create internal demand for economists. Kyle Kretschman:Yep. That's right. And that's, that's what I would say against from the process side. And then from the product side, that's using econometric research in the ways that I've been talking about it's using it both not only for individual analysis, but also then building econometric measurement systems that improve the product to get towards Spotify's mission of, of billion listeners and fans who can connect with over a million creative artists who are making a living. So that's, so it's a combination, it's the combination people process. Do we have the people set up? Do we have this integrated system of economists working alongside all these different types of stakeholders along with the product side of, do we have these measurement techniques that we're applying in a way that is important to Spotify's not only Spotify's business, but all the stakeholders that have an interest in Bon life. Scott Cunningham:So I feel like, you know, I think to academics that, that, and, and maybe even to some degree students, maybe I'm, maybe I'm completely an outlier here and I'm wrong, but you know, I think there's this like really shallow is a negative word. It, I mean, shallow, literally more and just like, it's just the thinnest knowledge possible of what exactly, you know, the, the, the core skillset of a successful economist is in tech. You know, and for many people they think, I think they, they think it's such a primitive level. They're like, it needs to be somebody that can code, you know, it's a data scientist, but, but it, but it, but that's not what I associate with economics. Right. So what would you, what would you articulate? It is, Kyle Kretschman:So it's the ability to do econom applied econometric research. That's applied to business problems. Mm. So within that is coding. Yes. Scott Cunningham:Right, right. Within that is coding. Kyle Kretschman:I, the vast majority, I won't say everyone, but the vast majority of tech economists are gonna have some level of coding and maybe they're not coding anymore. Like I'm not doing any coding anymore, but like they, they have that ability. So that's just again, that's, that's a skillset, but the real ability is doing long-term economic research. Because the questions that we get asked are very hard and difficult, and they are maybe in the academic setting, maybe they are publication worthy, takes that take three years, four years to actually solve with the right model. Yeah. But it's the ability to take that three year research roadmap and make it progress. So when you're doing that, you need to have your summary statistics that the business ca

Neste episódio, tivemos a oportunidade de bater um papo sobre desenvolvimento econômico, corrupção e políticas públicas com o pesquisador Dr. Claudio Ferraz. Conversamos sobre as mudanças na economia enquanto disciplina nas últimas décadas, a complexidade que envolve fatores econômicos, a distinção entre desenvolvimento e crescimento econômico, o impacto da corrupção no desenvolvimento econômico e a avaliação da eficácia de políticas públicas, no Brasil e no mundo. Dr. Claudio Ferraz é professor de Economia na Vancouver School of Economics, na Universidade de British Columbia. Também é professor no Departamento de Economia da PUC-Rio. Atualmente é Diretor Científico do J-PAL América Latina e Caribe, cuja missão é reduzir a pobreza garantindo que políticas sejam informada por evidências científicas, e codiretor da Rede de Economia Política da Associação Econômica da América Latina e do Caribe - LACEA e Instituto de Pesquisa para Desenvolvimento, Crescimento e Economia - RIDGE. É membro honorário da LACEA, membro da Econometric Society e atualmente editor associado da Econometrica, Journal of Political Economy e Journal of Development Economics. Sua pesquisa acadêmica se concentra em desenvolvimento econômico, economia política e economia pública. Em particular, estuda governança e prestação de contas nos países em desenvolvimento e as consequências para a política e a prestação de serviços públicos. -----------REFERÊNCIAS DO EPISÓDIO---------- Mais informações sobre Claudio Ferraz: https://sites.google.com/site/claudferraz/ -----------Cursos com Desconto------------ http://www.universogeneralista.com.br/curadoria-de-cursos/ ------------------Apoie o Canal------------ https://apoia.se/universogeneralista ------------------Youtube------------------ https://www.youtube.com/c/UniversoGeneralista ------------------Redes Sociais------------ https://www.instagram.com/universogeneralista/ https://twitter.com/UGeneralista -------- Tratamento de áudio ----------- Allan Spirandelli - https://www.instagram.com/allanspirandelli/ Spotify - https://sptfy.se/7mFh --------ASSUNTOS DO EPISÓDIO------- (0:00) Introdução (1:22) Currículo - Cláudio Ferraz (2:22) Histórico - Cláudio Ferraz (7:22) Curso de Economia na atualidade (13:19) Impacto da ideologia na ciência econômica (19:39) Complexidade de sistemas econômicos (27:06) Crescimento X Desenvolvimento Econômico (29:53) Economia do Brasil e suas peculiaridades (33:17) Políticas públicas para o desenvolvimento econômico (37:28) Análise política da economia e diferenças entre países (40:48) Corrupção e seu impacto no desenvolvimento econômico (50:16) Corrupção, gênero e idade (52:06) Políticas públicas de combate à corrupção (56:47) Corrupção e o impacto da punição (1:00:00) Conhecimento científico e políticas públicas (1:05:52) Avaliação das políticas públicas no Brasil (1:09:56) Programas de transferência de renda pelo mundo (1:13:28) Políticas públicas que não funcionam (1:17:55) O papel do FMI atualmente (1:21:00) A qualidade dos dados na ciência econômica (1:24:55) Como entender melhor a economia? (1:30:30) O que ainda não sabemos na ciência econômica? --- Send in a voice message: https://anchor.fm/universogeneralista/message

A Teoria dos Jogos tem mais aplicações na prática do que aquelas que podemos imaginar: está subjacente aos leilões de arte mas também aos leilões do peixe ou das flores; está por detrás da colocação de professores em escolas ou de médicos em hospitais. Até a turma onde a sua filha foi colocada na Faculdade é determinada por esta teoria que afinal tem aplicações muito mais concretas do que parece.Joana Pais e Hugo Van Der Ding largam o lado teórico e trocam agora a Teoria dos Jogos por miúdos, fazendo jus ao objectivo do IN PERTINENTE: dar respostas às perguntas de todos e contribuir para uma sociedade mais informada.REFERÊNCIAS E LINKS ÚTEIS:Leilões:Krishna, Vijay. Auction theory. Academic press, 2009. Milgrom, Paul Robert. Putting auction theory to work. Cambridge University Press, 2004 Desenho de mercados em geral:Roth, Alvin E. The economist as engineer: Game theory, experimentation, and computation as tools for design economics." Econometrica 70.4 (2002): 1341-1378.Roth, Alvin E. "What Have We Learned from Market Design?." The Economic Journal 118.527 (2008): 285-310. Scott Duke Kominers, Alexander Teytelboym, and Vincent P. Crawford. An invitation to market design. Oxford Review of Economic Policy Matching theory:Gale, David, and Lloyd S. Shapley. "College admissions and the stability of marriage." The American Mathematical Monthly 69.1 (1962): 9-15. Scientific Background on the Sveriges Riksbank Prize in Economic Sciences in Memory of Alfred Nobel 2012: https://www.nobelprize.org/uploads/2018/06/advanced-economicsciences2012.pdfRoth, Alvin E. "The evolution of the labor market for medical interns and residents: a case study in game theory." The Journal of Political Economy(1984): 991-1016. Alvin Roth, Marilda Sotomayor, Two-sided matching (1990), Cambridge university press (Econometric Society Monograph)Alvin Roth (2015), Who gets what - and why: The new economics of Matchmaking and Market Design, Eamon Dolan / Houghton Mifflin Harcourt Michael A. Rees, Ty B. Dunn, Christian S. Kuhr, Christopher L. Marsh, Jeffrey Rogers, Susan E. Rees, Alejandra Cicero, Laurie J. Reece, Alvin E. Roth, Obi Ekwenna, et al. Kidney exchange to overcome financial barriers to kidney transplantation. American Journal of Transplantation, 17:782–790, 2017.BIOSJOANA PAISJoana Pais é professora de Economia no ISEG da Universidade de Lisboa. Obteve o seu Ph.D. em Economia na Universitat Autònoma de Barcelona em 2005. Atualmente é coordenadora do programa de Mestrado em Economia e do programa de Doutoramento em Economia, ambos do ISEG, e membro da direção da unidade de investigação REM - Research in Economics and Mathematics. É ainda coordenadora do XLAB – Behavioural Research Lab, um laboratório que explora a tomada de decisão e o comportamento económico, político e social, suportado pelo consórcio PASSDA (Production and Archive of Social Science Data). Os seus interesses de investigação incluem áreas como a teoria de jogos, em particular, a teoria da afetação (matching theory), o desenho de mercados, a economia comportamental e a economia experimental.HUGO VAN DER DING Hugo van der Ding nasceu nos finais dos anos 70 ao largo do Golfo da Biscaia, durante uma viagem entre Amesterdão e Lisboa, e cresceu numa comunidade hippie nos arredores de Montpellier. Estudou História das Artes Decorativas Orientais, especializando-se em gansos de origami. Em 2012, desistiu da carreira académica para fazer desenhos nas redes sociais. Depois do sucesso de A Criada Malcriada deixou de precisar de trabalhar. Ainda assim, escreve regularmente em revistas e jornais, é autor de alguns livros e podcasts, faz ocasionalmente teatro e televisão, e continua a fazer desenhos nas redes sociais. Desde 2019 é um dos apresentadores do programa Manhãs da 3, na Antena 3.

Diego Puga's Favorite Urban Economics Papers of 2021 Diego Puga is Professor of Economics at CEMFI in Madrid, Spain. In recent years, he has made a tradition of sharing his favorite urban economics papers of the year (specifically, urban econ articles published in the calendar year). In this interview, we chat about his favorites from 2021. They appear below as well as in this thread. He did similar threads for 2020, 2019, and 2018. Diego's Ten Favorite Urban Econ Articles Published in 2021: The Internal Spatial Organization of Firms: Evidence from Denmark by Camilo Acosta and Ditte Håkonsson Lygnemark in the Journal of Urban Economics. Location as an Asset by Adrien Bilal and Esteban Rossi-Hansberg in Econometrica. The Production Function for Housing: Evidence from France by Pierre-Philippe Combes, Gilles Duranton, and Laurent Gobillon in the Journal of Political Economy. Are Poor Cities Cheap for Everyone? Non-Homotheticity and the Cost of Living Across U.S. Cities by Jessie Handbury in Econometrica. East-Side Story: Historical Pollution and Persistent Neighborhood Sorting by Stephan Heblich, Alex Trew, and Yanos Zylberberg in the Journal of Political Economy. Building the City: From Slums to a Modern Metroplis by J. Vernon Henderson, Tanner Regan, and Anthony J. Venables in the Review of Economic Studies. Planning Ahead for Better Neighborhoods: Long-Run Evidence from Tanzania by Guy Michaels, Dzhamilya Nigmatulina, Ferdinand Rauch, Tanner Regan, Neeraj Baruah, and Amanda Dahlstrand in the Journal of Political Economy. The Effect of High-Tech Clusters on the Productivity of Top Inventors by Enrico Moretti in the American Economic Review. Commuting and Innovation: Are Closer Inventors More Productive? by Hongyu Xiao, Andy Wu, and Jaeho Kim in the Journal of Urban Economics. The Economics of Speed: The Electrification of the Streetcar System and the Decline of Mom-and-Pop Stores in Boston, 1885-1905 by Wei You in the American Economic Journal: Applied Economics. Appendices: Diego Puga: Provides examples of areas where urban economists could benefit from more interaction with urban planners to get better information about whether new initiatives are actually doing what we claim they do, including superblocks in Barcelona and the 15 Minute City in Paris. Eg: Super Blocks in Barcelona; The 15 Minute City. Greg Shill: Musings on the Boston streetcar paper (Economics of Speed), Location as an Asset, and the interaction between real estate prices and firm experimentation, noting the role of Kaldi's, a local coffee roaster/distributor, in raising the floor for the quality of coffee at locations in St. Louis (where Greg is visiting at Washington University School of Law this semester). Eg: an interview with the founder. Jeff Lin: On (Not) Reading Papers by Jan Hendrik Kirchner and Reading Books Versus Engaging With Them by Holden Karnofsky. Follow us on the web or on Twitter: @denselyspeaking, @jeffrlin, @greg_shill, and @ProfDiegoPuga Producer: Schuyler Pals. The views expressed on the show are those of the participants, and do not necessarily represent the views of the Federal Reserve Bank of Philadelphia, the Federal Reserve System, or any of the other institutions with which the hosts or guests are affiliated.

הפרק דיברנו על למה הכאב מהפסד עולה בעוצמתו על השמחה שברווח.שנאת הפסד היא תופעה מעניינת העוסקת בא-סימטריה ביחס שלנו כלפי רווחים והפסדים.דיברנו על:איך שנאת הפסד משפיעה על התנהגות של משקיעים?מה גרם לסטודנטים להירשם בזמן לכנס בכלכלה התנהגותית?מדוע מדליית כסף יותר מאכזבת ממדליית ארד?ומה הקשר בין שנאת הפסד למאפייני אישיות?בקיצור, לא כדאי לפספס! :)~~~

This is the second episode of a book club series on Peter Gärdenfors's book Conceptual Spaces. In this episode, we will discuss chapters 3 and 4, in which Gärdenfors explains how properties and concepts fit into his theory of conceptual spaces.For this series, I'm joined by Koen Frolichcs, who was already my cohost for the books club series on Lee Child's Killing Floor. Koen and I are PhD students in the same lab.Podcast linksWebsite: https://geni.us/bjks-podTwitter: https://geni.us/bjks-pod-twtKoen's linksGoogle Scholar: https://geni.us/frolichs-scholarTwitter: https://geni.us/frolichs-twtBen's linksWebsite: https://geni.us/bjks-webGoogle Scholar: https://geni.us/bjks-scholarTwitter:  https://geni.us/bjks-twtReferencesGärdenfors, P. (2004). Conceptual spaces: The geometry of thought. MIT press. Kahneman, D, & Tversky, A (1979). Prospect Theory: An Analysis of Decision under Risk. Econometrica. 47 (2): 263–291. Kriegeskorte, N., Mur, M., & Bandettini, P. A. (2008). Representational similarity analysis-connecting the branches of systems neuroscience. Frontiers in systems neuroscience, 2, 4. Montague, P. R., Dayan, P., Person, C., & Sejnowski, T. J. (1995). Bee foraging in uncertain environments using predictive hebbian learning. Nature, 377(6551), 725-728.Murphy, R. O., & Ackermann, K. A. (2014). Social value orientation: Theoretical and measurement issues in the study of social preferences. Personality and Social Psychology Review, 18(1), 13-41.https://en.wikipedia.org/wiki/Monotonic_function

The issue of income inequality is one Americans continually wrestle with the COVID 19 pandemic bringing to light how housing, health, and general wellbeing are impacted by the unequal distribution of wealth. Income inequality in the United States is the focus of this episode of Stats and Stories with guest Joseph Gastwirth. Dr. Gastwirth is a Professor of Statistics and Economics at George Washington University. Over the course of his career he has written over 300 peer-reviewed articles, which have appeared in the Annals of Statistics, Journal of the American Statistical Association, Journal of the Royal Statistical Society, Econometrica, Review of Economics and Statistics, Statistical Science, Annals of Human Genetics, Human Heredity, Jurimetrics and Statistics and Public Policy. His research has covered a variety of topics in statistical methodology and applications. Of special note are: his early work on order and non-parametric statistics, his research on estimating measures of economic inequality, fairness and discrimination and on the role of statistical evidence in jury discriminations, equal employment and other types of legal cases. The American Statistical Association awarded him Noether Award for his contributions to nonparametric statistics in 2012 and the Karl E. Peace Award for outstanding statistical contributions for the betterment of society in 2019.

Keno Juechems is a Junior Research Fellow at St John's College in Oxford. He studies how humans make decisions, using computational modelling, behavioural tasks, and fMRI. In this conversation, we talk about his papers  "Optimal utility and probability functions for agents with finite computational precision" and  "Where does value come from?", and various related topics.BJKS Podcast is a podcast about neuroscience, psychology, and anything vaguely related, hosted by Benjamin James Kuper-Smith. New episodes every Friday. You can find the podcast on all podcasting platforms (e.g., Spotify, Apple/Google Podcasts, etc.).Timestamps0:00:05: Where does the name "Keno" come from?0:01:47: How Keno got into his current research area0:14:09: Start discussing Keno's paper "Optimal utility and probability functions for agents with finite computational precision"0:26:46: Rationality and optimality0:38:58: Losses, gains, and how much does a paper need to include?0:51:04: Start discussing Keno's paper "Where does value come from?"1:10:28: How does a PhD student learn all this stuff?1:19:56: Resources for learning behavioural economics and reinforcement learning1:25:42: What's next for Keno Juechems?Podcast linksWebsite: https://bjks.buzzsprout.com/Twitter: https://twitter.com/BjksPodcastKeno's linksWebsite: https://www.sjc.ox.ac.uk/discover/people/keno-juchems/Google Scholar: https://scholar.google.de/citations?user=tereY1oAAAAJTwitter: https://twitter.com/kjuechemsBen's linksWebsite: www.bjks.blog/Google Scholar: https://scholar.google.co.uk/citations?user=-nWNfvcAAAAJTwitter:  https://twitter.com/bjks_tweetsReferencesJuechems, K., & Summerfield, C. (2019). Where does value come from?. Trends in cognitive sciences.Juechems, K., Balaguer, J., Spitzer, B., & Summerfield, C. (2021). Optimal utility and probability functions for agents with finite computational precision. Proceedings of the National Academy of Sciences.Kahneman, D., & Tversky, A. (1979). Prospect theory: An analysis of decision under risk. Econometrica.Keramati, M., & Gutkin, B. (2014). Homeostatic reinforcement learning for integrating reward collection and physiological stability. Elife.Lewis, M. (2016). The undoing project: A friendship that changed the world. Penguin UK.Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.Thaler, R. H. (2015). Misbehaving: The making of behavioral economics.Trepte, S., Reinecke, L., & Juechems, K. (2012). The social side of gaming: How playing online computer games creates online and offline social support. Computers in Human behavior.https://en.wikipedia.org/wiki/Indifference_curveDavid Silver's reinforcement learning course on YouTube: https://www.youtube.com/watch?v=2pWv7GOvuf0&list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQChris Summerfield's course How to Build a Brain: https://humaninformationprocessing.com/teaching/

There is an interesting philosophy about how to make things better called Meliorism. Yup. It just might...make your brain happy. Instagram: http://instagram.com/happybrainfm Heather's Instagram: https://www.instagram.com/heatherparady/ Website: http://tlbc.co/happy-brain RESOURCES: Connect with Sara Soyeju: www.ediblepsych.com Sara.soyeju@ediblepsych.com Instagram & Facebook @ediblepsychology Work Mentioned: Pawelski, J. O. (2006, March). Mitigation and construction: Toward a balanced meliorism. Paper presented at the annual meeting of the Society for the Advancement of American Philosophy. San Antonio, TX. (Very Academic) Kahneman, D., & Tversky, A. (1979). Prospect theory: An analysis of decision under risk. Econometrica, 47, 263-291. (Lay person-ish) Kahneman, D. (2011). Thinking, fast and slow. Farrar, Straus and Giroux. (PERMA) Seligman, Martin E. P. Learned Optimism: How to Change Your Mind and Your Life. New York: Vintage Books, 2006 --- This episode is sponsored by · Anchor: The easiest way to make a podcast. https://anchor.fm/app

Speaker: Chang-Tai Hsieh, Phyllis and Irwin Winkelried Professor of Economics and PCL Faculty Scholar, The University of Chicago Booth School of Business We use administrative registration records with information on the owners of all Chinese firms to document the importance of “connected” investors, defined as state-owned firms or private owners with equity ties with state-owned firms, in the businesses of private owners. We document a hierarchy of private owners: the largest private owners have direct investments from state-owned firms, the next largest private owners have equity investments from private owners that themselves have equity ties with state owners, and the smallest private owners do not have any ties with state owners. The network of connected private owners has expanded over the last two decades. The share of registered capital of connected private owners increased by almost 20 percentage points between 2000 and 2019, driven by two trends. First, state-owned firms have increased their investments in joint ventures with private owners. Second, private owners with equity ties to state owners also increasingly invest in joint ventures with other (smaller) private owners. The expansion in the “span” of connected owners from these investments with private owners may have increased the aggregate output of the private sector by 4.2% a year between 2000 and 2019. Chang-Tai Hsieh conducts research on growth and development. His published papers include “The Life-Cycle of Plants in India and Mexico,” in the Quarterly Journal of Economics; “Misallocation and Manufacturing TFP in China and India,” in the Quarterly Journal of Economics; “Relative Prices and Relative Prosperity,” in the American Economic Review; “Can Free Entry be Inefficient? Fixed Commissions and Social Waste in the Real Estate Industry,” in the Journal of Political Economy; “What Explains the Industrial Revolution in East Asia? Evidence from the Factor Markets,” in the American Economic Review; “The Allocation of Talent and US Economic Growth,” in Econometrica; “How Destructive is Innovation?” in Econometrica; and “Special Deals with Chinese Characteristics,” in the NBER Macroeconomics Annual. Hsieh has been a visiting scholar at the Federal Reserve Banks of San Francisco, New York, and Minneapolis, as well as the World Bank’s Development Economics Group and the Economic Planning Agency in Japan. He is a Research Associate for the National Bureau of Economic Research, a Senior Fellow at the Bureau for Research in Economic Analysis of Development, and a member of the Steering Group of the International Growth Center in London. He is the recipient of an Alfred P. Sloan Foundation Research Fellowship, an Elected Member of Academia Sinica, and the recipient of the Sun Ye-Fang award for research on the Chinese economy.

O paper dessa semana bombou no #EconTwitter e tá pra ser publicado na Econometrica!!! Em "Redistribution through Markets", is autores argumentam que políticas que distorcem o mercado - como controle de preços e racionamento - podem ser socialmente desejáveis em cenários com desigualdade elevada. Quer entender melhor a ideia? Vem comigo!!

Rafael Dix-Carneiro é economista internacional da Universidade Duke, na Carolina do Norte. Sua pesquisa foi publicada nos principais periódicos de economia, como o American Economic Review e a Econometrica e é referência obrigatória em qualquer texto ou curso sobre comércio internacional. Rafael é engenheiro elétrico formado pela PUC-Rio, mestre em Matemática pelo IMPA e Doutor em Economia pela Universidade Princeton, em Nova Jérsei. Além de Duke, ele trabalhou em Yale, Maryland e no Banco Mundial.Principais artigos mencionados:* Trade liberalization and labor market dynamics (2014), Econometrica* Trade liberalization and the skill premium: A local labor markets approach (2015), AER PP (com B Kovak)* Trade liberalization and regional dynamics (2017), AER (com B Kovak)* Economic shocks and crime: Evidence from the brazilian trade liberalization (2018), AEJ: Applied (com G Ulyssea e R Soares)* Margins of labor market adjustment to trade (2019), JIE (com B Kovak)

De fleste gennemgange af økonomiens teorihistorie slutter med Keynes' død. Det gør vores også. Næsten. Vi tager også et temaafsnit om Chicago-økonomerne. Inden vi kommer så langt, vil jeg i dagens afsnit lave et lille eksperiment. Jeg vil komme med et meget kort overslag over nogle af de vigtige teoretiske udviklinger indenfor økonomi fra 1946 og frem til nu. Det er et eksperiment, fordi jeg udelukkende bruger min egen hukommelse med en forudsætning om, at jeg må have huske noget af det væsentligste. Der er sikkert meget, der er glemt, men i hvert fald kommer vi igennem as-if-economics, adfærdsøkonomi, eksperimenter, entreprenørens genfødsel og meget mere. Der er sikkert noget, som jeg har glemt, men så vil det med garanti blive dækket i næste sæson, hvor jeg og min nye medvært Otto Brøns vil tale om alle nobelprismodtagerne i rækkefølge. Glæd dig! Har du nogensinde tænkt over, hvad økonomi er for en videnskab? Hvordan opstod den, og hvem var dens grundlæggere? Eller har du interesseret dig for moderne diskussioner om samfundet, herunder ulighed, ressourceforbrug eller konkurrence? Hvis dette er tilfældet, er økonomiens teorihistorie vigtig og nyttig for dig. Den type af diskussioner er nemlig mindst lige så gammel som den økonomiske videnskab selv, og du vil i dens rødder også finde rødderne til de moderne argumenter. Til dagens afsnit har jeg læst:  Artinger, F., Petersen, M., Gigerenzer, G., & Weibler, J. (2015). Heuristics as Adaptive Decision Strategies in Management. Journal of Organizational Behavior, s. 33-52. Becker, G. S. (1993). The Economic Way of Looking at Behavior. Journal of Political Economy, s. 385-409. Boettke, P. (2017). Don't Be a "Jibbering Idiot": Economic Principles and the Properly Trained Economist. The Journal of Private Enterprise, s. 9-15. Bruni, L., & Sugden, R. (2007). The Road Not Taken: How Psychology Was Removed From Economics, and How It Might Be Brought Back. The Economic Journal, s. 146-173. Camerer, C. (1999). Behavioral Economics: Reunifying Psychology and Economics. Proceedings of the National Academy of Sciences of the USA, s. 10575-10577. Coase, R. (1937). The Nature of the Firm. Economica, s. 386-405. Conlisk, J. (1996). Why Bounded Rationality? Journal of Economic Literature, s. 669-700. De Martino, B., Kumaran, D., Seymour, B., & Dolan, R. J. (2006). Frames, Biases, and Rational Decision-Making in the Human Brain. Science, s. 684-687. Friedman, M. (1953). Essays in Positive Economics. Chicago: University of Chicago Press. Gul, F., & Pesendorfer, W. (2008). The Case for Mindless Economics. The Foundations of Positive and Normative Economics, s. 3-42. Hayek, F. A. (1948). Individualism and Economic Order. Chicago: University of Chicago Press. Kahneman, D., & Tversky, A. (1979). Prospect Theory: An Analysis of Decisions Under Risk. Econometrica, s. 263-291. Kirzner, I. M. (1973). Competition and Entrepreneurship. Chicago: The University of Chicago Press. Shane, S., & Venkataraman, S. (2000). The Promise of Entrepreneurship as a Field of Research. Academy of Management Review, s. 217-226. Smith, V. L. (2003). Constructivist and Ecological Rationality in Economics. The American Economic Review, s. 465-508. Todd, P. M., & Gigerenzer, G. (2007). Environments That Makes Us Smart: Ecological Rationality. Current Directions in Psychological Science, s. 167-171. Williamson, O. (1996). Economics and Organization: A Primer. California Management Review, s. 131-146. I like to dedicate this season to my teachers Ole Bruus and Bruce Caldwell. All mistakes and mispronunciations are mine alone and no fault of theirs.

This week, Matt Egan in CNN Business wrote a piece called “Americans create new economic threat with their own savings.” In it, he wrote that credit card debt is declining as American’s are spending less AND are paying down their balances.This information piled on top of a conversation we had on our other podcast, Behavioral Grooves, with Mariel Beasley, the Director of the Center for Advanced Hindsight at Duke University. She shared current research that lower-to-middle income Americans are saving MORE during the pandemic.On one hand, that’s totally rational because we don’t know how long the crisis is going to last and we need to save for what will sure to be additional expenses. On the other hand, increasing your savings when you don’t have a job doesn’t make sense.In this Weekly Grooves, we discuss some of the research literature on scarcity, fear, and the common mistake made by gamblers to place risky bets when their winnings are down. We also discuss the possibility of anticipated regret as a possible explanation for savings behaviors.We hope you enjoy it and that you’ll share this episode with a friend.© 2020 Weekly Grooves LinksEgan, Matt, “Americans create new economic threat with their own savings” CNN, May 12, 2020: https://www.cnn.com/2020/05/12/investing/jobs-coronavirus-consumer-spending-debt/index.htmlCarrns, Ann, “How to Build an Emergency Fund in the Middle of an Emergency,” The New York Times, March 20, 2020: https://www.nytimes.com/2020/03/20/your-money/coronavirus-emergency-fund.html “Each extra dollar saved” reduces the likelihood of having to skip bill payments, said Mariel Beasley, a co-founder of Common Cents Lab, a financial research group at Duke University.Kahneman, Daniel, & Tversky, Amos, Prospect theory: An analysis of decision under risk. Econometrica, 47, 263–291, 1979: https://www.uzh.ch/cmsssl/suz/dam/jcr:00000000-64a0-5b1c-0000-00003b7ec704/10.05-kahneman-tversky-79.pdfLoudenback, Tanza, “The pandemic spurred Americans to finally start saving money, but it's unclear how long the new habit will last,” Business Insider, May 14, 2020:  https://www.businessinsider.com/personal-finance/us-savings-accounts-increase-during-pandemic-emergency-funds-2020-5Shafir, Eldar, “The Psychology of Scarcity,” American Psychological Association, February 2014:  https://www.apa.org/monitor/2014/02/scarcityWeber, Bethany & Chapman, Gretchen, “Playing for peanuts: Why is risk-seeking more common for low-stakes gambles?” Organizational Behavior and Human Decision Making, 2003: https://tinyurl.com/y884upe7“Covid-19 Crisis: Mariel Beasley on Increasing Short Term Savings During the Crisis,” Behavioral Grooves, May 13, 2020, episode 146: https://behavioralgrooves.com/episode/covid-19-crisis-mariel-beasley-on-increasing-short-term-savings-during-the-crisis/Unemployment Rates in the United States from 1929 to 2019: https://www.thebalance.com/unemployment-rate-by-year-3305506Behavioral Grooves: https://behavioralgrooves.com/Kurt Nelson, PhD: @whatmotivatesTim Houlihan: @THoulihan

Entrevista de Nico Yacoy en Viva la Pepa! a Ramiro Castiñeira, economista de Econometrica, por la inflacion y Alberto Fernandez

Robert Frank, the Henrietta Johnson Louis Professor of Management and Professor of Economics at the Cornell Johnson Graduate School of Management, returns to Present Value to discuss his new book Under the Influence: Putting Peer Pressure to Work. The conversation explores the nature of social contagion and its numerous implications for how we approach public policy - most importantly our response to climate change. Professor Frank breaks down the mechanics of social contagion, what our regulatory approach has missed in the past, and how we can leverage knowledge of the tendency to mimic others to confront climate threats moving forward. For more than a decade, Professor Frank’s "Economic View" column appeared monthly in The New York Times. He received his BS in mathematics from Georgia Tech, and then taught math and science for two years as a Peace Corps Volunteer in rural Nepal. He holds an MA in statistics and a PhD in economics, both from the University of California at Berkeley. His papers have appeared in the American Economic Review, Econometrica, Journal of Political Economy, and other leading professional journals. His books have been translated into 23 languages, including Choosing the Right Pond, Passions Within Reason, Microeconomics and Behavior, Principles of Economics (with Ben Bernanke), Luxury Fever, What Price the Moral High Ground?, Falling Behind, The Economic Naturalist, The Darwin Economy, and Success and Luck. The Winner-Take-All Society, co-authored with Philip Cook, received a Critic's Choice Award, was named a Notable Book of the Year by The New York Times, and was included in Business Week's list of the ten best books of 1995. Frank is a co-recipient of the 2004 Leontief Prize for Advancing the Frontiers of Economic Thought. He was awarded the Johnson School's Stephen Russell Distinguished teaching award in 2004, 2010, and 2012, and its Apple Distinguished Teaching Award in 2005. Links from the Episode at presentvaluepodcast.com Book Link: Under the Influence: Putting Peer Pressure to Work (Amazon Link) Episode Article: Johnson Business Feed Profile: Robert H. Frank - Johnson  Twitter: @econnaturalist

www.patreon.com/electricvehiclepodcast ☝Support this podcast & get all unlisted episodesWhy do people refuse to drive electric? The bias for the status quo (oil-based transportation system) has many reasons. It could be the result of a rational analysis of benefits and cost. But it could also be the result of an irrational commitment to previous decisions, or due to cognitive misperception.Contact InformationE-Mail: electric-vehicle-podcast@outlook.comWebsite: www.electric-vehicle-podcast.comTwitter: teresa_rhoferFacebook: ElectricVehiclePodcastReferences[1] H. A. Simon, Models of man; social and rational. Oxford, England: Wiley, 1957.[2] L. Festinger and J. Carlsmith, “Cognitive Consequences of Forced Compliance,” Journal of Abnormal and Social Psychology, vol. 58, pp. 203–210, 1959.[3] D. Kahneman and A. Tversky, “Prospect Theory: An Analysis of Decision under Risk,” Econometrica, vol. 47, no. 2, pp. 263–292, 1979. MusicDigital Future Technology [audiojungle]

Voici donc la deuxième partie de notre entretien avec Clémence Tricaud, doctorante au CREST et à l'école Polytechnique. Dans cet épisode, nous analysons les résultats obtenus par Clémence et son co-auteur, Vincent Pons, professeur à la Harvard Business School, dans leur papier paru dans Econometrica, intitulé "Le vote expressif et ses conséquences : analyse des seconds tours de scrutin comptant deux ou trois candidats". La question consiste à se demander si les électeurs préfèrent exprimer leur préférence réelle et voter pour le candidat qu’ils préfèrent au risque de “gâcher” leur voix, ou s'ils votent de manière stratégique pour un autre candidat, qui a plus de chances de remporter l'élection. Autrement dit, les électeurs sont-ils plutôt expressifs ou stratégiques? Nous verrons que cela semble influencer les résultats de nombreuses élections, souvent dans un sens qui reflète moins bien l'avis de la majorité, ce qui incite à remettre en question le scrutin uninominal utilisé dans la plupart des démocraties. En particulier, nous nous penchons sur deux modes de scrutin alternatifs, moins soumis au dilemme du vote utile: le jugement majoritaire, et le scrutin de Condorcet randomisé. Rejoignez-nous pour la deuxième partie de cet entretien, depuis votre plateforme d'écoute de podcast préférée ! Liens cités dans l'épisode: La note de Clémence Tricaud et Vincent Pons pour l'Institut des Politiques Publiques : https://www.ipp.eu/wp-content/uploads/2019/05/n40-notesIPP-mai2019.pdf Leur papier d'origine, dans Econometrica, y compris les annexes et fichiers de réplication : https://onlinelibrary.wiley.com/doi/abs/10.3982/ECTA15373 Une présentation du scrutin au jugement majoritaire: https://fr.wikipedia.org/wiki/Jugement_majoritaire Le livre Jugement Majoritaire, par Michel Balinski et Rida Laraki: https://www.amazon.fr/Majority-Judgment-Measuring-Ranking-Electing/dp/0262015137/ref=cm_cr_srp_d_product_top?ie=UTF8 Une vidéo sur le jugement majoritaire (issue d'une série passionnante sur la démocratie à l'angle de la théorie des jeux): https://www.youtube.com/watch?v=_MAo8pUl0U4 Une présentation du scrutin de Condorcet randomisé: https://fr.wikipedia.org/wiki/Scrutin_de_Condorcet_randomis%C3%A9 Une vidéo sur le scrutin de Condorcet randomisé (issue d'une série passionnante sur la démocratie à l'angle de la théorie des jeux): https://www.youtube.com/watch?v=wKimU8jy2a8 Un site pour organiser vos propres scrutins de Condorcet randomisés dans votre vie quotidienne: http://votation.ovh/

Dans ce premier épisode post-élections, nous avons le plaisir de recevoir Clémence Tricaud, doctorante au CREST et à l'école Polytechnique. Cette interview sera découpée en deux parties. Le présent épisode revient sur le parcours de Clémence, comment elle en est venue à étudier l'économie politique, et ce qu'elle fait au jour le jour. Nous discutons aussi de ce que fait un doctorant concrètement - qu'est-ce que ça veut dire "être chercheur" ? - et de ce que signifie la méthode scientifique - quel est le but de la recherche en économie ? Quels sont ses outils et méthodes ? Comment mettre en évidence des causalités plutôt que des corrélations ? Rejoignez-nous pour la première partie de cet entretien, depuis votre plateforme d'écoute de podcast préférée ! Liens cités dans l'épisode: La note de Clémence Tricaud et Vincent Pons pour l'Institut des Politiques Publiques : https://www.ipp.eu/wp-content/uploads/2019/05/n40-notesIPP-mai2019.pdf Leur papier d'origine, dans Econometrica, y compris les annexes et fichiers de réplication : https://onlinelibrary.wiley.com/doi/abs/10.3982/ECTA15373 Le site et les travaux de Paul Romer, prix Nobel d'économie 2018 : https://paulromer.net/jupyter-mathematica-and-the-future-of-the-research-paper/ et https://qz.com/1417145/economics-nobel-laureate-paul-romer-is-a-python-programming-convert/ The Atlantic, The Scientific Paper Is Obsolete : https://www.theatlantic.com/science/archive/2018/04/the-scientific-paper-is-obsolete/556676/

Bloomberg Opinion columnist Barry Ritholtz interviews Joshua Miller, an economics professor at the University of Alicante whose research interests include behavioral economics and decision theory. His paper "Surprised By the Hot Hand Fallacy? A Truth in the Law of Small Numbers," co-authored with Adam Sanjurjo, recently appeared in the journal Econometrica. 

Dans plusieurs pays de destination, les immigrés ont une tendance à habiter en proximité d'autres immigrés, souvent du même groupe ethnique. Les politiques publiques d'intégration sociale peuvent influencer ces dynamiques de ségrégation urbaine. Le but de cette présentation est de résumer la littérature économique récente concernant les effets de la ségrégation urbaine sur la situation des immigrés sur le marché du travail et la scolarisation de leurs enfants. Sans aborder les aspects méthodologiques et techniques, la communication a comme objectif de discuter les effets de voisinage et les conséquences économiques de vivre dans une enclave ethnique, à l'aide des résultats des études empiriques pour les pays scandinaves (Edin et al., 2003 QJE), la France (Algan, Hémet et Laitin, 2014; Goux et Maurin, 2007 EJ) et les Etats-Unis (Katz et al., 2007 Econometrica, sur le programme Moving to Opportunity).

Jeffrey Kling, Associate Director for Economic Analysis at the Congressional Budget Office, is an economist who joined CBO in July 2009. He has conducted research on public housing, incarceration, retirement security, Medicare's prescription drug program, unemployment insurance, and other aspects of public policy in the United States. His work has been published in the American Economic Review, Econometrica, the Quarterly Journal of Economics, and elsewhere. Previously, he was the Joseph A. Pechman Senior Fellow and Deputy Director of Economic Studies at the Brookings Institution. From 1998 to 2005, he was a faculty member at Princeton University. In earlier government service, he was a special assistant to the Secretary of Labor and an assistant to the chief economist at the World Bank. He earned his Ph.D. in economics from the Massachusetts Institute of Technology, and his A.B. from Harvard University. His presentation will focus on CBO’s use of evidence in the analysis of budget and economic policies. The presentation will addressed numerous questions, including: How does CBO make projections? What types of evidence does CBO use?How does CBO characterize uncertainty?Recorded Dec 12, 2011http://www.national-economists.org/podcasts/nec192.mp3

Garett Jones of George Mason University talks with EconTalk host Russ Roberts about the ideas of Irving Fisher on debt and deflation. In a book, Booms and Depressions and in a 1933 Econometrica article, Fisher argued that debt-fueled investment booms lead to liquidation of assets at unexpectedly low prices followed by a contraction in the money supply which leads to deflation and a contraction in the real side of the economy--a recession or a depression. Jones then discusses the relevance of Fisher's theory for the current state of the economy in the aftermath of the financial crisis.

Garett Jones of George Mason University talks with EconTalk host Russ Roberts about the ideas of Irving Fisher on debt and deflation. In a book, Booms and Depressions and in a 1933 Econometrica article, Fisher argued that debt-fueled investment booms lead to liquidation of assets at unexpectedly low prices followed by a contraction in the money supply which leads to deflation and a contraction in the real side of the economy--a recession or a depression. Jones then discusses the relevance of Fisher's theory for the current state of the economy in the aftermath of the financial crisis.

Garett Jones of George Mason University talks with EconTalk host Russ Roberts about the ideas of Irving Fisher on debt and deflation. In a book, Booms and Depressions and in a 1933 Econometrica article, Fisher argued that debt-fueled investment booms lead to liquidation of assets at unexpectedly low prices followed by a contraction in the money supply which leads to deflation and a contraction in the real side of the economy--a recession or a depression. Jones then discusses the relevance of Fisher's theory for the current state of the economy in the aftermath of the financial crisis.

Narayana Kocherlakota became president and chief executive officer of the Federal Reserve Bank of Minneapolis on October 8, 2009. Kocherlakota has served as a professor of economics at the University of Minnesota since 2005, where he chaired the department from 2006-2008. Since 1999 he has also served as a consultant to the Federal Reserve Bank of Minneapolis. From 1996-98, he was a research staff member at the Bank. He is also a research associate at the National Bureau of Economic Research. Kocherlakota has published more than 30 articles in academic journals, including Econometrica, Journal of Political Economy, Journal of Economic Theory, Journal of Monetary Economics and Journal of Money, Credit and Banking. His work includes theoretical and empirical contributions to macroeconomics, monetary economics, financial economics and public finance. Kocherlakota has authored a forthcoming book from Princeton University Press titled The New Dynamic Public Finance, which describes an approach to tax design pioneered by him and others over the past decade. Kocherlakota earned a Ph.D. in economics from the University of Chicago in 1987 and an A.B. in mathematics from Princeton in 1983.