17 février 2007

Astrology study proves a point

TORONTO, Feb. 17 (UPI) -- Tongue firmly in cheek, a Canadian researcher said Virgos are more likely to vomit while pregnant, while Pisces have an increase risk of heart failure.

Peter Austin, a researcher at the Institute for Clinical Evaluative Sciences in Toronto, said data gleaned from Ontario hospitals reveal the 12 astrological signs can be associated with at least two disorders each.

But, he said, his research was intended to prove a point, not about astrological signs, but about research.

"Replace astrological signs with another characteristic such as gender or age, and immediately your mind starts to form explanations for the observed associations," Austin said.

"Then we leap to conclusions, constructing reasons for why we saw the results we did. We did this study to prove a larger point -- the more we look for patterns, the more likely we are to find them, particularly when we don't begin with a particular question."

Copyright 2007 by United Press International. All Rights Reserved.

Le phénomène décrit dans cet article est simple: si l'on prend une population donnée et que l'on cherche des associations quelconques, on finira par en trouver une qui correspond à nos préjugés et qui sera 'statistiquement significative', bien qu'étant totalement sans aucun rapport avec la réalité. Pour éviter ça, il faut dire a priori quelle association on recherche et faire l'étude après.