Wednesday 30 June 2010

Damned statistics

Further to the interesting discussions in these pages about statistics and epidemiology, here is a recent letter published in The Spectator (not available online). The correspondent goes a little further in his criticisms than I would, nevertheless, it bears repeating...


As an engineer, scientist and mathematician, I am completely in agreement with Rod Liddle's view  of statistics. I have long argued, with anyone who cares to listen (and plenty who don't), that any statistic should be completely ignored if it doesn't come with a 1,000-page manual describing exactly how it was arrived at and what it means. And that manual should be read, pored over and discussed for at least ten years.

The human race has survived and flourished for hundreds of thousands of years without statistics. We survive using superstition, lust, greed and envy. All that statistics have done is make life miserable by legitimising with dubious science the personal biases of busybodies. It tells us that we shouldn't drink, shouldn't smoke and shouldn't immunise our children with the MMR vaccine. Lie, damned lies and statistics.

Dr Tom Roberts


Mark Wadsworth said...

I'd question the "hundreds of thousands of years" figure, whence did he pluck that? Can he prove it? Define 'year', etc.

Smoking Hot said...

lf only Dr Roberts, if only. :)

Anonymous said...

Rod Liddle's "Monty Hall Problem" example is one of my favorite anecdotes. I first read about it in the book "The Curious Incident of the Dog in the Night Time".

It isn't so much the counter-intuitive solution to the problem, but the letters Vos Savant received from thousands of experts telling her she was wrong (when she was demonstrably right), and the admonishing tone with which they were written.

So much for "consensus".


Fredrik Eich said...

I think Rod Liddle's two jacks and an ace version is a good way of showing the Monty Hall Problem.
But then the whole pack of cards can be used to make someone understand it very quickly because after they have picked one card of 52 leaving a pile of 51 and a pile of 1; and after you remove 50 cards from the 51 pile to leave a pile of 1 and 1; It does not take much to work out that you should choose the pile that had 50 other cards excluded!

Anonymous said...

Glad to see such letters appearing and hope Dr Tom Roberts will speak out more often and in greater detail.
The Monty Hall problem is also a favourite of mine and Rod Liddle's version of it is good. However I think he, Alex Bellos and Gary Foshee are wrong in thinking that the two boys problem is the same. In the comments to Rod Liddle's article, Malcolm Price
June 29th, 2010 2:48pm gives a detailed explanation of the error. Given that many mathematicians have come a cropper over the Monty Hall problem, it is not surprising that he falls short of condemning Rod and the others.
I have always considered probability to be a very slippery subject and statistical analysis to be a huge house of cards built on top of it.