This post was inspired after a conversation I had earlier with a few people. It has been brought to my attention that Eoin Clarke, who blogs at The Green Benches, is a frequent abuser of statistics.
All of us have been guilty at one time or another of fudging statistics, usually through omission, for the purpose of an argument. In this I am reminded of an Anchorman scene:
Brian Fantana: …She gets a special cologne. It’s called Sex Panther by Odeon. It’s illegal in nine countries. Yep. It’s made with bits of real panther, so you know it’s good.
Ron Burgundy: It’s quite pungent. It’s a formidable scent; it stings the nostrils in a good way.
Brian Fantana: Yup.
Ron Burgundy: Brian, I’m gonna be honest with you, that smells like pure gasoline.
Brian Fantana: They’ve done studies, you know. 60% of the time, it works every time.
Ron Burgundy: That doesn’t make any sense.
Brian Fantana: Well, let’s go see if we can make this little kitty purr.
Statistics have become abused so frequently that they are losing their significance.
I don’t know why statistics are being abused. I can only put it down to ignorance. Ignorance of the people who abuse the statistics, and ignorance of people who read the “analysis”. I know that the country has a maths problem, more a fear than an actual inability to calculate and analyse. It is this fear, and a fear to question statistics, which allows the pedlars of misinformation to prevail.
The latest statistic which is doing the rounds at the moment is: “9 out of 10 hospital doctors oppose the NHS bill” An alarming figure for anyone who happens to catch the headline. However, the body of the article does not discuss the sample size meaning that one can’t weight the survey. It does, however, indicate that the poll was carried out by callonyourcollege.blogspot.com who use the Survey Monkey tool. Therefore one has to assume that the sample is very small and probably not at all representative of hospital doctors.
The survey was open access, so there could have been no attempt at proper sampling and contained no demographic information that could have been used to weight it. It should go without saying that a survey from a website campaigning against the NHS reforms and co-ordinating opposition to it amongst the Medical Royal Colleges is more likely to be found and completed by opposed to the bill (in much the same way that a poll carried out on, say, the Conservative party’s website, might be considerably more supportive).
The moral of this story is to be cautious of statistics and question the methods of data collection. Question the motives of the data collector and, above all, learn some statistics.