One term in stats class and the world's your oyster
Unfortunately, many researchers looking for risk factors for diseases are not aware that they need to modify their statistics when they test multiple hypotheses. The consequence of that mistake, as John Ioannidis of the University of Ioannina School of Medicine, in Greece, explained to the meeting, is that a lot of observational health studies—those that go trawling through databases, rather than relying on controlled experiments—cannot be reproduced by other researchers. Previous work by Dr Ioannidis, on six highly cited observational studies, showed that conclusions from five of them were later refuted. In the new work he presented to the meeting, he looked systematically at the causes of bias in such research and confirmed that the results of observational studies are likely to be completely correct only 20% of the time. If such a study tests many hypotheses, the likelihood its conclusions are correct may drop as low as one in 1,000—and studies that appear to find larger effects are likely, in fact, simply to have more bias. - The Economist, February 22, 2007I wonder why a good statistics course is not part of more colleges' "core" or distribution requirements. I mean, besides the fact that students might start avoiding any college that was going to make them take a statistics course.
But it's hard to think of an area where even very sophisticated, educated people make fundamental reasoning errors due to simple ignorance. See also my recent post about what Larry Summers said (also mentioning the base-rate fallacy). Most people have no idea what the margin of error in opinion polls is telling them, have never considered the logic of causal order, etc.
posted at 1:59 PM
2 Comments:
You kissin' up to Dr. Lala? 'Cause that's what this seems like.
I think that would require me to have the slightest idea what you are talking about ;)
Teletubbies?
Post a Comment
<< Home