无序样品聚类分析——基于第二组距离法和质心法  

Cluster analysis of disordered samples:based on the methods of the second set of distances and the centroid method

作　　者：胡纯严 胡良平 Hu Chunyan;Hu Liangping(Graduate School,Academy of Military Sciences PLA China,Beijing 100850,China;Specialty Committee of Clinical Scientific Research Statistics of World Federation of Chinese Medicine Societies,Beijing 100029,China)

机构地区：[1]军事科学院研究生院,北京100850 [2]世界中医药学会联合会临床科研统计学专业委员会,北京100029

出　　处：《四川精神卫生》2024年第S1期78-83,94,共7页Sichuan Mental Health

摘　　要：本文目的是介绍与无序样品聚类分析有关的基本概念、计算方法、两个实例以及使用SAS实现计算的方法。基本概念包括相似性、相异性、度量型和非度量型;计算方法涉及度量两个样品之间距离的第二组距离法(共12个)和度量两类样品之间距离的质心法(centroid法);两个实例分别为“1982年我国16个地区农民支出情况的调查数据”以及“13个运动项目在两项定量指标上的测定值”;借助SAS软件,对两个实例的数据进行了无序样品聚类分析,并对SAS输出结果做出了解释。The purpose of the paper was to introduce the basic concepts,calculation methods,two examples and the implementation of SAS calculation methods related to the cluster analysis of disordered samples.The basic concepts included similarity,dissimilarity,metric and non metric type.The calculation methods involved the second set of distance methods(12 in total)for measuring the distance between two samples and the centroid method for measuring the distance between two clusters of samples.The data in the two examples were"survey data on the expenditure of farmers in 16 regions of China in 1982"and"measurement values of 13 sports events on two quantitative indicators".Using SAS software,cluster analysis of disordered samples was performed on the data from two instances,and the SAS output results were explained.

关 键 词：距离 相异性 非度量型 谱系聚类分析 树形图 

分 类 号：R195.1[医药卫生—卫生统计学]