Is science being corrupted by misinerpretation of statistics (Introduction)

by xeno6696 , Sonoran Desert, Thursday, April 08, 2010, 19:16 (5342 days ago) @ David Turell

A fascinating essay on how scientists (especially medical ones) misinterpret the use of p values, how it affects drug trials, genetic studies of gene function, etc. I'm sure Matt will not be surprised at the opinions presented.
> 
> 
> http://www.sciencenews.org/view/feature/id/57091/title/Odds_Are,_Its_Wrong-ESPECIALLY this line: -Replicating a result helps establish its validity more securely, but the common tactic of combining numerous studies into one analysis, while sound in principle, is seldom conducted properly in practice.-It is this property that underpins many global warming arguments, and has been used (in my opinion) as a cheap tactic to get published without having to do any real work. -Most of this article underlines a previous set of statements I've made in here that deal with how null-hypothesis testing works. (Or should work.) -I KNOW for a fact that a strong foundation in logic isn't part of the curriculum for any of the students in my college, and the abuse of statistics is one of the end results of this. Even I--someone trained in computer science who speaks the language of logic as a near-native speaker can get tripped up in this game. So, the fact that many people are truly untrained in its use underlines why bad science happens. -Great article David, I hope more people read it.

--
\"Why is it, Master, that ascetics fight with ascetics?\"

\"It is, brahmin, because of attachment to views, adherence to views, fixation on views, addiction to views, obsession with views, holding firmly to views that ascetics fight with ascetics.\"