Feb 24, 2009

cause and effect

not so long ago, researchers (many of whom in the pay of the tobacco companies) still found it possible to claim that smoking and lung cancer weren't necessarily causally connected. in 1959, cornfield, haenszel, hammond, lilienfeld, shimkin, and wynder wrote a comprehensive, scrupulously researched paper revealing the shaky methodological ground on which these dissenting studies were built, and it is a spectacularly clear, well-written paper. for most of it, they restrain themselves from outright criticism even when richly deserved but, towards the end, clearly the temptation become irresistible:

A universe in which cause and effect always have a one-to-one correspondence with each other would be easier to understand, but it obviously is not the kind we inhabit.
a comparison to the people who insist that climate change is bogus would not here, i think, be invidious.

No comments: