One of the hard things when reading articles or research is to figure out what’s actually going on. How much better is this new treatment? How big is the risk of adverse effects? Is there any clinical significance? Should I change my practice? Will I ever stay awake long enough to read a proper book on statistics? Luckily, I found a great blog article that¬†explains how risk can be communicated, and how to put that spin on risk.

2845 ways to spin the risk
The blog Understanding Uncertainty has a piece called 2845 ways to spin the Risk. It’s a great article explaining this dry material in a way that’s easy to read and easy to understand. No mean feat. So go read it!

It’s what we’ve tried to learn before: relative risk, absolute risk, number needed to treat. Put up on pie charts, columns and smiley faces. Angled as a positive or negative expression. But put into an interactive diagram making it easier and more intuitive to compare the different ways of looking at risk. It’s a little eye opener.

Mismatched framing – a common spin
When publishing results in a paper, I guess it’s quite natural to try to boast your findings, underplaying side effects. The way to do this can be to present the positive findings and negative side effects in different ways – spin the risk. “This will tend to exaggerate the benefits, minimise the harms, and in any case make it unable to compare them. This is known as ‘mismatched framing’, and was found in a third of studies published in the British Medical Journal“.

This article will teach you all the dirty little tricks, from changing the scales of your column chart to enhance small differences, to changing from a negative to a positive view – a 5% risk of getting the disease to a 95% chance of staying healthy. Using absolute and relative risk to your advantage, and swapping between them as you see fit. The article is a great refresher, a presenting statistics 101.

Pimp my chart
The interactive chart has bacon sandwich causing bowel cancer and statins saving you from heart attack as examples, but you can even put in your own theory or finding to play around with and spin any way you like. Open the interactive diagram in its own window here, but do go and read the article first.

This entry was posted in Statistics and tagged . Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *