合理进行多元分析——变量聚类分析

Reasonably carry out multivariate analysis:variable clustering analysis

本文目的是介绍与变量聚类分析有关的基本概念、计算方法、两个实例以及SAS实现。基本概念包括变量聚类分析、相似系数、变量聚类方法、类成分和类结构;计算方法涉及相似系数法计算过程和特征值法计算过程;两个实例涉及的资料分别是“60名正常男性10项指标的测定结果”和“36只兔子的7项指标测定结果”;借助SAS对两个实例中的定量资料进行了全面的变量聚类分析,并对输出结果给出了解释。

The purpose of this article was to introduce the basic concepts,calculation methods,two examples and SAS implementation related to the variable cluster analysis.Basic concepts included variable cluster analysis,similarity coefficient,variable clustering methods,class composition and class structure.The calculation approaches involved the calculation process of the similarity coefficient method and the eigenvalue method.The data involved in the two examples were measurement results of 10 related indicators in 60 normal males and measurement results of 7 indicators in 36 rabbits.With the help of SAS software,a comprehensive variable cluster analysis was carried out on the quantitative data in the two cases,and a reasonable explanation was given for the output results.