如何正确运用χ^(2)检验——三种双向无序二维列联表资料的χ^(2)检验  

How to useχ^(2) test correctly——χ^(2) tests for the data collected from the three kinds of two dimensional contingency tables without ordinal variables in two directions

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》2021年第2期111-115,共5页Sichuan Mental Health

摘　　要：本文目的是介绍除四格表资料之外的三种双向无序二维列联表资料的χ^(2)检验以及SAS与R软件实现的方法。三种双向无序二维列联表是指双向无序的"R×2""2×C"和"R×C"(R与C均大于2)列联表。一般来说,分析它们的目的都是检验列联表中两属性变量是否独立,在满足特定前提条件时,可以选用的简单统计分析方法为χ^(2)检验;在不满足特定前提条件时,应当选择计算量非常大的Fisher’s精确检验法。The purpose of this article was to introduce theχ^(2) test and SAS and R software implementation of three kinds of two-way unordered two-dimensional contingency table data except the four-fold table data.The three kinds of the tables referred to the two-way unordered"R×2""2×C"and"R×C"(both R and C were greater than 2)contingency tables.Generally speaking,the purpose of analyzing them was to test whether the two attribute variables in the contingency table were independent.When certain prerequisites were met,the simple statistical analysis method that could be used was theχ^(2) test,when the specific prerequisites were not met,the Fisher’s exact test,which required the large amount of calculation,should be selected.

关 键 词：二维列联表 前提条件 独立性 χ^(2)检验 SAS软件 R软件 

分 类 号：R195.1[医药卫生—卫生统计学]