无序样品聚类分析——基于斜交空间和平均距离法  

Cluster analysis of disordered samples:based on the methods of oblique intersection space distance and the average distance

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66-70,共5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R2统计量、半偏R2统计量、伪F统计量和伪t2统计量;计算方法涉及斜交空间距离计算公式和平均距离计算公式;两个实例分别为“某地1962年—1988年三化螟种群消长资料”和“10种红葡萄酒在6项指标上的得分”;借助SAS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 calculation methods using SAS related to the cluster analysis of disordered samples.Basic concepts included R2 statistic,semi-partial R2 statistic,pseudo F statistic and pseudo t2 statistic.The calculation methods involved the oblique intersection space distance calculation formula and the average distance calculation formula.The data in the two examples were"population growth and decline data of stem borer in a certain area from 1962 to 1988"and"scores of 10 types of red wines on 6 indicators".With the help of SAS software,cluster analysis of disordered samples was performed on the data in the two examples,and the explanation of the SAS output results was given.

关 键 词：无序样品 斜交空间距离 平均距离 聚类分析 树形图 

分 类 号：R195.1[医药卫生—卫生统计学]