MULTIPLE COMPARISON METHODS - ESTABLISHING GUIDELINES FOR THEIR VALID APPLICATION IN NEUROPSYCHOLOGICAL RESEARCH

被引：98

作者：

CICCHETTI, DV ^{[1
]}

机构：

[1] YALE UNIV,W HAVEN,CT

来源：

JOURNAL OF CLINICAL AND EXPERIMENTAL NEUROPSYCHOLOGY | 1994年 / 16卷 / 01期

关键词：

D O I：

10.1080/01688639408402625

中图分类号：

B849 [应用心理学];

学科分类号：

040203 ;

摘要：

This comment serves to provide a rationale for research clinical neuropsychologists to decide: (1) under what conditions multiple comparison methods are required; and (2) what specific guidelines can be used to distinguish conditions favoring a given multiple comparison technique over its competitors. The topic is discussed both for the parametric and nonparametric case, as well as for post hoc tests following both statistically significant main effects and interactions.

引用

页码：155 / 161

页数：7

共 78 条

[1] TYPE-I ERROR RATES FOR YAO AND JAMES TESTS OF EQUALITY OF MEAN VECTORS UNDER VARIANCE-COVARIANCE HETEROSCEDASTICITY [J].