David Spiegelhalter on Communicating Statistics

LISTEN TO DAVID SPIEGELHALTER NOW!

While they aren’t as unpopular as politicians or journalists, people who work with statistics come in for their share of abuse. “Figures lie and liars figure,” goes one maxim. And don’t forget, “There are three kinds of lies: lies, damned lies, and statistics.”

But some people are the good guys, doing their best to combat the flawed or dishonest use of numbers. One of those good guys is David Spiegelhalter, professor of the public understanding of risk in the Statistical Laboratory in the Centre for Mathematical Sciences at the University of Cambridge and current president of the Royal Statistical Society. Spiegelhalter, the subject of this Social Science Bites podcast, even cops to being a bit of an “evidence policeman” because on occasion even he spends some of his time “going around telling people off for bad behavior.”

There is bad behavior to police. “There’s always been the use of statistics and numbers and facts as rhetorical devices to try and get people’s opinion across, and to in a sense manipulate our emotions and feelings on things,” he tells interviewer David Edmonds. “People might still think that statistics and numbers are cold, hard facts but they’re soft, fluffy things. They can be manipulated and changed, made to look big, made to look small, all depending on the story that someone wants to tell.”

Asked at one point if he even accepts that there are ‘facts,’ Spiegelhalter gives a nuanced yes. “I’m not going to get into the whole discussion about ‘what is truth,’ although it’s amazing how quick you do go down that line. No, there are facts, and I really value them.”

Despite that policing role, Spiegelhalter explain, his methods are less prescriptive and more educational, working to get others to ask key questions such as “What am I not being told?” and “Why I am hearing this?” The goal is less to track down every bit of fake news in the world, and more to inoculate others against its influence.

One part of that, for example, is determining what communicators and organizations to trust. Spiegelhalter, acknowledging his debt to Onora O’Neill, an emeritus professor of philosophy at the University of Cambridge, argues that organizations themselves shouldn’t strive to be trusted, but to show trustworthy attributes. This goes beyond things like “fishbowl transparency,” where you lard your website with every imaginable factoid, but actively making sure people can get to your information, understand it and they can assess how reliable it is.

That ‘understanding’ part of the process is what Spigelhalter pursues as part of chairing the Winton Centre for Risk and Evidence Communication, which is dedicated to improving the way that quantitative evidence is used in society. In that role he’s become a public face of honest use of numbers, as evidenced by his role as presenter of the BBC4 documentaries Tails you Win: the Science of Chance and Climate Change by Numbers. His own research focuses on health-related use of statistics and statistical methods, and while that might include Bayesian inference using Gibbs samplinig, it can also encompass the focus of his 2015 book, Sex by Numbers.

To download an MP3 of this podcast, right-click HERE and save.

***

For a complete listing of past Social Science Bites podcasts, click HERE. You can follow Bites on Twitter @socialscibites and David Edmonds @DavidEdmonds100.