APPLICATION OF OPTIMAL SIGN-VECTORS TO RELIABILITY AND CLUSTER-ANALYSIS

被引：2
作者：
WOODWARD, JA
BENTLER, PM
机构：
[1] Department of Psychology, University of California, Los Angeles, 90024, California
来源：
PSYCHOMETRIKA | 1979年 / 44卷 / 03期
关键词：
classification; cluster analysis; optimal weights; reliability;
D O I：
10.1007/BF02294698
中图分类号：
O1 [数学];
学科分类号：
0701 ; 070101 ;
摘要：
Expressions involving optimal sign vectors are derived so as to yield two new applications. First, coefficient alpha for the sign-weighted composite is maximized in analogy to Lord's scale-independent solution with differential weights. Second, optimal sign vectors are used to define two groups of objects that are maximally distinct in terms of a function of the squared euclidean distances between groups. An efficient computing algorithm is described along with several examples. © 1979 The Psychometric Society.
引用
收藏
页码：337 / 341
页数：5
相关论文
共 7 条
1