Understanding Data in the Media

Data experts Ted Dunning and Ellen Friedman discuss how data is used in today's digital society. They examine the enormous potential offered by big data, explain the new technologies that enable real time analytics and explore best practices for transforming how we plan large-scale computing projects.

Dr Mark Taylor - Lecturer in Quantitative Methods at the Sheffield Methods Institute explains how to understand the use of small numbers in this excerpt from our new free, open online course 'Making Sense of Data in the Media.'

Dr Mark Taylor - Lecturer in Quantitative Methods at the Sheffield Methods Institute explains how to break down bigger numbers in this excerpt from our new free, open online course 'Making Sense of Data in the Media.'

Data experts Ted Dunning and Ellen Friedman discuss how data is used in today's digital society. They examine the enormous potential offered by big data, explain the new technologies that enable real time analytics and explore best practices for transforming how we plan large-scale computing projects.

In this video, we hear from Joe Twyman, the Head of Political and Social Research for Europe, Middle East and Africa at YouGov (an internet-based market research company) about his experience of conducting research through surveys.Joe explains some of the basic principles of surveying, why web-based surveys are an increasingly important mode of survey data collection and how to read survey results properly.

A sample is a subset of a population. It lies at the heart of survey research. It is sometimes called a ‘miniature of the population’, so the process of drawing a sample should maximise the similarity between the population under study and the sample.In this video, educator Aneta Piekut looks at how we select the members of the population to achieve this goal.

This is a phrase used in statistics to emphasise that a correlation between two variables does not imply that one causes the other. Just because two trends seem to fluctuate in tandem, that doesn’t prove that they are meaningfully related to one another.In this video, Todd explains the difference between correlation and causation and advises caution whenever you see an eye-catching headline suggesting that one activity leads to another.

Most reputable organisations will provide some level of information about the data they publish so that we can see how it was collected, who procured it, and for what purpose. Without this basic information, we should be wary of any results drawn from this data. This information is often described in the ‘Methodology’ section of a document (i.e. news article, survey report, academic paper) and it is crucial to whether we should trust the data.In this video, Todd Hartman explains some of the important questions a reliable methodology section should answer:- WHO sponsored the study, and who collected the data?- WHAT is the sample size?- WHEN was the data collected or observed?- WHERE is the data from?- HOW was the data collected?- WHY was the data collected?

Measurement is how we quantify objects and events so that we can make comparisons among them. Being aware of the measures used in a dataset will help you determine the quality of the evidence.

What happens when a research question isn’t framed properly? You can end up with misleading conclusions.In this video, educator Andy Bell considers a recent news story and the research question (or questions) that lie behind it.

We’ve started to get a sense of some of the different ways that the media uses data to make you think numbers are big or small, but sometimes, to understand the size of a number, we need to compare it to something else.In this video, Mark introduces some useful comparisons for particular kinds of data - such as comparing to other countries and looking back through time.

Another way that the media uses data is to report change and risk - how much has something increased or decreased? If you start a particular behaviour, how much does that increase your risk of a particular outcome? As we saw earlier, when numbers are stripped of context, it can be difficult to tell whether they are as dramatic as they seem. This is even more strongly the case when we look at differences between percentages or differences without a common baseline, as in the case of risk.In this video, Mark explains the difference between percentage increases and percentage point increases and between absolute and relative risk. Don’t worry if you don’t quite catch these concepts first time round, we’ll revisit them in the next step to make sure you’re following.

It may sound like a silly question, but if we want to make sense of data in the media, then whenever we hear numbers quoted, one of the first things we should be asking is - is that a big number? If someone’s spending money on you, they’re likely to want to make that figure sound as impressive as possible; on the other hand, if someone wants you to spend your money on them, they’ll want to make that figure sound as small as possible.In this video, Mark explains some of the ways that big numbers can be made to sound small and small numbers can be made to sound big.

Does 0.1% sound like a big number? Stripped of important context, it’s almost impossible to tell.Context is crucial in understanding whether numbers are big or not, particularly when it comes to percentages. 2% might sound like a small number of people, but if it’s of all people in the world, it’s a lot; 80% might sound like a lot of people, but if it’s of the people who work in your office; it’s a lot less. Whenever we see percentages quoted, we should be asking “as a percentage of what?”, “how much does 100% actually correspond to?” and “what is 100%; a number of people, a sum of money, or something else?”.In this video, Mark demonstrates how numbers can look big or small in relation to the whole ecosystem in which they sit.

Learn how to make sense of social statistics and economic data with this introductory course on quantitative social science.https://www.futurelearn.com/courses/media-dataIncreasingly, we’re bombarded with all sorts of data about how society is changing: opinion poll trends, migration data, economic results, government debt levels and MPs’ expenses claims. The ability to read such information with confidence is an increasingly important skill for both modern citizens and those studying the social sciences.In this free online course, we’ll look at ways of cutting through the confusion to decide what numbers reveal, and when and why they (sometimes deliberately) mislead.