Behavioral and Brain Sciences



Open Peer Commentary
Chow: Statistical significance

Null-hypothesis tests are not completely stupid, but Bayesian statistics are better


David Rindskopf a1
a1 Educational Psychology, City University of New York Graduate Center, New York, NY 10036 drindsko@email.gc.cuny.edu

Abstract

Unfortunately, reading Chow's work is likely to leave the reader more confused than enlightened. My preferred solutions to the “controversy” about null- hypothesis testing are: (1) recognize that we really want to test the hypothesis that an effect is “small,” not null, and (2) use Bayesian methods, which are much more in keeping with the way humans naturally think than are classical statistical methods.