Ever wondered where urban myths come from? Well, one strong contender might be press releases. We have spotted this article in the Guardian which provides excellent insight into the misuse of statistics which may lie beneath many a misleading headline.
On reading a press release from the Institute of Advancd Motorists (IAM) which referred to 57% of bike riders – nationally – admitting to jumping red lights, Peter Walker smelt a rat and instinctually started asking questions.
Q. Where did the figure come from? A. A recent ’poll’ of 1600 people. Q. What sort of poll was this? A. Responses to a survey monkey poll on the IAM’s own website. SO not exactly a random sample then….more of a self selecting group (and one, which although very unlikely, could have included respondents who were all members of the anti-cycling lobby).
Worse…..if the press release made it sound like 57% of cyclists jump lights regularly, when you actually broke the figures down, they showed that 1.9% confessed to this. Another 11.8% did so “sometimes” while 24.6% did “rarely”, and 19.1% had done so once or twice.
In summary, it’s clear that most of us have a strong interest in knowing if and how many cyclists are jumping lights and it’s wrong that misleading headlines – based on poorly interpreted data – are allowed to stand in the way of good information.
N.B. We have since learned that once the mistake was brought to their attention, the IAM re-issued the press release with a more nuanced introduction “57 % of of cyclists say they have jumped a red light at least once, with 14 % saying they do so regularly or sometimes, according to the IAM’s latest online poll of 1600 people”. It also referenced the ”32% of drivers who say they jump lights”.
However, the press release headline still maintains that ”More than half of cyclists jump red lights”. It will be interesting to see how this is reported tomorrow.
See the RSS-getstats ‘CIPR, MRS and RSS’ ‘Best practice guide for using statistics in communications’ for PR colleagues writing press releases.
Print 
PDF
There seems to have been a response with most people reporting the 14% figure high up in the article. This is a good thing and would be worth reporting if this was a reasonable inference about the population. Sadly it isn’t and that hasn’t been picked up. 14% would be better to remember than 57% but it’s still not a reliable inference for a national population. The figure of 1600 respondents is being touted as if a decent sample size was sufficient justification to generalise to the national population of cyclists. Internet surveys are not normally representative and they are also open to deceitful responses which would bias the results. More to the point, most people observe the cyclists on their daily commute but not any others, so the relevance of a statistic for the national population is fairly niche. Most people commenting on the Guardian article are interested in the comaparbility of the 57% statistic to their daily experience.
Looking at google’s news stuff, few papers have actually reported the story with several of those who have noting the statistical issues. Fullfact have reported on it and even the Daily Mail hasn’t been ridiculous – I suspect the controversy has taken away the interest and 14% isn’t a very exciting figure. It seems criticising a press release can make a difference – who knew?