Day By Day

Sunday, March 04, 2007

The Continuing Collapse of Scientific Authority -- The Misuse of Statistics

The Economist explains Why so much medical research is rot:

[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... on six highly cited observational studies, showed that conclusions from five of them were later refuted.... [N]ew work... 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.

So, the next time a newspaper headline declares that something is bad for you, read the small print. If the scientists used the wrong statistical method, you may do just as well believing your horoscope.

Read the whole thing here.

Incompetence and unscrupulousness on the part of researchers and the ignorance of journalists who report on them are undermining the integrity of scientific authority in a number of fields, most importantly in medical and environmental studies. Nearly every week the public is bombarded with new "studies" that purport to prove all matter of things. Most of these are rubbish, but they are avidly seized upon and enlisted in current political and cultural debates. Inevitably this hucksterism obscures the real value of scientific research and debases the entire scientific enterprise.

No comments: