[email protected] wrote: > Alerted by a colleague, I recommend an instructive if > depressing essay on the problematic use of statistics in science. > > http://www.sciencenews.org/view/feature/id/57091/title/Odds_ar > e,_its_w or http://tinyurl.com/yh7sk7r > >
Yikes. What a simultaneously bizarre and ordinary column. There is little here that hasn't been written about and widely known since the 1960s. Except that the author sensationally attributes the problem to "statistics"rather than specifically to the null hypothesis significance test (NHST). The fact that he then advocates Bayesian statistic (which have also been widely written about, though not much used in psychology, since the 1960s) makes the point as effectively as I could. Correct probabilistic reasoning can be difficult, to be sure (as Kahneman & Teversky; Gigerenzer, et al.; etc. have long shown us). But many kinds of mathematical and scientific reasoning are difficult. That's why we have special institutions with highly-paid instructors to teach them. That doesn't make statistics a "mutant form of math" (an accusation that sounds more like it comes form the first half of the 19th century, than form the start of the 21st). The rise of probabilistic reasoning was probably the greatest epistemological advance in history since the invention of calculus. Anyone who thinks otherwise should try doing, say, evolutionary theory or quantum mechanics without it. (Not to mention pretty well all of social and behavioral science, of course.) Chris -- Christopher D. Green Department of Psychology York University Toronto, ON M3J 1P3 Canada 416-736-2100 ex. 66164 [email protected] http://www.yorku.ca/christo/ ========================== --- You are currently subscribed to tips as: [email protected]. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5&n=T&l=tips&o=1427 or send a blank email to leave-1427-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
