Bacon butties and a tiger’s lunch – the PR challenges of communicating stats

My study window looks out over a hedge to fields. Though, today, the view is brought short by a bank of fog.

Each morning a neighbour’s cat sits and stares at the sparrows that come and go. They seem untroubled by his presence: to be honest, I’m not really sure he knows what he’s doing.

I guess both birds and cat are acting on their instincts.

This got me thinking about the excellent book, The Tiger That Isn’t, by Michael Blastland and Andrew Dilnot. They created – and for a number of years, presented – Radio 4’s More or Less programme. The latter has gone on to head up the UK Statistics Authority.

The back page blurb has a comment from David Dimbleby:

“Explains to us laymen how to make sense of numbers and how we can avoid having the wool pulled over our eyes”.

I agree (though I wonder if that’s ‘we laypeople’ not ‘us laymen’?!?).

We are, the authors set out on page 45, “gifted recognisers of patterns and the moments when a pattern is interrupted”. They go on to explain that some experts have said that the processes of evolution explain this – “better to identify [a] pattern in the trees as a tiger … than to assume that what we see is a chance effect of scattered light and shifting leaves in the breeze, creating an illusion of stripes”.

The light and leaves gave our very distant ancestors data that, on analysis, they needn’t act upon. But if they hadn’t would they have been lunch for a ravenous big cat – and, in turn, ourselves just what might have been many generations along?

These days the suburbs are not troubled by anything more felinely ferocious than next door’s Tiddles. But we retain our pattern spotting skills. And, in our data-rich world, we still have the problems of working out which patterns are due to real circumstances and which the result of chance.

Last week, much news coverage focused on the announcement by the International Agency for Research on Cancer (IARC) that eating processed meat can, indeed, cause cancer. How many bacon butties is too many bacon butties troubled the nation for a day.

Such conclusions come from sophisticated statistical analysis. But, as Ed Yong in an article on theatlantic.com complained: “they [IARC] are terrible at communicating their findings”.

PR practitioners need some comfort with statistical basics

The analysis and conclusions will come from statistical experts using sophisticated techniques. But Yong’s complaint highlights the need for such experts to be working with communications experts – and the latter demands people who are up to speed with statistical concepts.

This doesn’t mean PR practitioners have to have insight into the deeper aspects of hypothesis testing, Bayesian analysis, and multivariate regression. But practitioners should have some comfort with basic concepts of experimental measurements and the datasets they yield – distributions, averages, uncertainty and the like.

As for cats and birds…. they can probably stick with their instincts.

Advertisements

Leave a comment

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s