Website review: Bayesian Critique of Statistics in ...
yarikoptic discovered this in Science/Tech
•1 reviews since Oct 2, 2006
science
•cs.ucsd.edu/users/goguen/courses/275f00/stat....
People who like this website
StumbleUpon is the best way to discover great web sites, videos, photos, blogs and more - based on your interests.
Everything is submitted and rated by the community. Discover, share and review the best of the web!
Reviews of this website
yarikoptic discovered 22 months ago- Indeed, blind use of statistics can do harm. Accounting for prior information using Bayes' theorem sounds like a good treat but the problem is again "what prior?". From the page 'Over the next 30 years, other statisticians also sounded the alarm bell, again without effect. During the 1980s, Prof James Berger of Purdue University - a world authority on Bayes's Theorem - published an entire series of papers alerting researchers to the "astonishing" tendency of the standard statistical tests to mislead. 'Significant evidence'," Berger warned, "can actually arise when the data provide very little or no evidence in favour of an effect." The warning could not have been clearer. But again, it was ignored.'
