心理学中对假设检验一些批评的分析

Analyses of Some Criticisms About Hypothesis-test in Psychology

根据假设检验原理的贝叶斯统计的表达方式分析和回应了心理学中对传统的假设检验方法的主要批评。认为:(1)确定假设的接受域不仅要考虑,同时也应该考虑以及这个假设的先验概率,而元分析方法的提出可看作对先验概率考虑的必然的逻辑结果;(2)零假设是可以接受的,但它的接受域只是备择假设接受域余集的一个子集;(3)传统的假设检验方法需要其他方法的补充。

Based on the principles of hypothesis-test in terms of Beyasian statistics, the article analysized and replied to psychological researchers＇ main criticisms about the classical hypothesis-test method. And the following conclusions were reached： （1）determining the accept-area for a hypothesis requires taking into account not only a, but also β and the prior-probability of the hypothesis and the production of meta-analysis may been seen as an inevitable logical result of taking the prior-probability into account; （2）null hypothesis can be accepted, but its accept-area is only a subset of the surplus-set of the accept-area for alternative hypothesis; （3）the classical hypothesis-test method can still be used in psychological research, but it should be suplemented by other data processing methods.