Statistics without probability: Significance testing as typicality and exchangeability in data analysis

Journal/Book: Behav Brain Sci. 1998; 21: 40 West 20TH Street, New York, NY 10011-4211. Cambridge Univ Press. 225.

Abstract: Statistical significance is almost universally equated with the attribution to some population of nonchance influences as the source of structure in the data. But statistical significance can be divorced from both parameter estimation and probability as, instead, a statement about the atypicality or lack of exchangeability over some distinction of the data relative to some set. From this perspective, the criticisms of significance tests evaporate.

Note: Editorial Vokey JR, Univ Lethbridge, Dept Psychiat & Neurosci, Lethbridge, AB T1K 3M4, CANADA

Zurück | Weiter