Of Nulls and Norms

Abstract

Neyman-Pearson methods in statistics distinguish between Type I and Type II errors. Through rigid control of Type I error, the "null" hypothesis typically receives the benefit of the doubt. I compare philosophers' interpretations of this feature of Neyman-Pearson tests with interpretations given in statistics textbooks. The pragmatic view of the tests advocated by Neyman, largely rejected by philosophers, lives on in many textbooks. Birnbaum thought the pragmatic view has a useful "heuristic" role in understanding testing. I suggest that it may have the opposite effect.