如何正确运用χ^(2)检验--高维表资料危险率差分析与SAS实现  

How to useχ^(2) test correctly--the analysis of a common risk difference for the data of a multiway table and the implementation of SAS software

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4期308-313,共6页Sichuan Mental Health

摘　　要：本文目的是介绍g×2×2表资料的危险率差分析方法和基于SAS软件实现计算的方法。需要完成的任务包括以下两项:其一,共同危险率差的点估计及其置信区间估计,其二,检验“共同危险率差是否等于0”。其中,实现前述第一项任务的方法共有6种,实现第二项任务的方法共有3种。本文基于SAS软件和一个实例,分别实现了共同危险率差的点估计、置信区间估计和假设检验,并对SAS输出结果进行了解释,做出统计结论和专业结论。The purpose of this article was to introduce the risk rate difference analysis method of the g×2×2 table data and the calculation method based on the SAS software.The tasks that needed to be completed included the following two terms:first,the point estimation of the common risk rate difference and its confidence interval estimation;second,the test"whether the common risk rate difference was equal to 0".Among them,there were a total of 6 approaches for achieving the aforementioned first task;and three approaches for achieving the aforementioned second task.Based on the SAS software and an example,the article realized the point estimation,the confidence interval estimation and the hypothesis test of the common risk rate difference,respectively.Next,the SAS output results were explained and the statistical and professional conclusions were made.

关 键 词：共同危险率差 置信区间 假设检验 标准正态分布 

分 类 号：R195.1[医药卫生—卫生统计学]