无序样品聚类分析——基于第三组距离法和类平均法  

Cluster analysis of disordered samples:based on the methods of the third set of distances and the average linkage 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84-89,共6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。基本概念包括对称名义变量、缺失值、匹配系数和海曼(Hamann)系数;计算方法涉及第三组距离法(共8个)和类平均法(average法);两个实例分别为“反映美国39座城市空气污染情况的调查数据”和“某地1962年—1988年三化螟种群消长资料”;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 this article 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 symmetric nominal variables,missing values,matching coefficients,and Hamann coefficients.The calculation method involved the third set of distance method(8 in total)and average linkage method.The data in the two examples were"survey data reflecting the air pollution conditions in 39 cities in the United States"and"population growth and decline data of stem borer in a certain area from 1962 to 1988".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：对称名义变量 匹配系数 海曼系数 谱系聚类分析 树形图 

分 类 号：R195.1[医药卫生—卫生统计学]