EXPLORING THE REPLICABILITY OF A STUDYS RESULTS - BOOTSTRAP STATISTICS FOR THE MULTIVARIATE CASE

被引：29

作者：

THOMPSON, B ^{[1
]}

机构：

[1] BAYLOR COLL MED,HOUSTON,TX 77030

来源：

EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT | 1995年 / 55卷 / 01期

关键词：

D O I：

10.1177/0013164495055001008

中图分类号：

G44 [教育心理学];

学科分类号：

0402 ; 040202 ;

摘要：

Conventional statistical significance tests do not inform the researcher regarding the likelihood that results will replicate. One strategy for evaluating result replicability is to employ a ''bootstrap'' resampling of a study's data so that the stability of results across numerous configurations of the subjects can be explored. This article illustrates the use of the bootstrap in a canonical correlation analysis.

引用

页码：84 / 94

页数：11

共 44 条

[1]

BARTKO JJ, 1991, AM PSYCHOL, V46, P1089

[2] CASE AGAINST STATISTICAL SIGNIFICANCE TESTING [J].