如何正确运用χ^(2)检验——配对设计四格表资料的χ^(2)检验  

How to use χ^(2) test correctly——χ^(2) test for the data of four-fold table collected from the matched pairs design

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1期44-47,共4页Sichuan Mental Health

摘　　要：本文目的是介绍配对设计四格表资料的McNemar΄s χ^(2)检验及SAS和R软件实现。首先,提出配对设计四格表资料存在3种情形,即①特设“金标准”的配对设计四格表资料,值得进行统计分析;②缺乏“金标准”的配对设计四格表资料,不值得进行统计分析;③隐含“金标准”的配对设计四格表资料,值得进行统计分析。其次,以第1种情形的“问题与数据”为统计分析的对象,分别采用SAS与R软件进行差异性分析,得出了计算结果,对结果作了解释,并给出了统计和专业结论。The purpose of this paper was to introduce the McNemar΄sχ^(2) test and SAS and R software implementation of four-fold table data collected from the matched pairs design.Firstly,it was proposed that there were three situations for the data of four-fold table of the paired design,namely①the data of paired design four-fold table with the special"gold standard"was worthy of statistical analysis;②the data of four-fold table of the paired design without the special"gold standard"was not worthy of statistical analysis;③the data of four-fold table collected from the matched pairs design with implicit"gold standard"was worthy of statistical analysis.Secondly,taking the"problems and data"in the first case as the object of statistical analysis,SAS and R software were used to analyze the differences,the calculation results were given and explained,and the statistical and professional conclusions were also made.

关 键 词：配对设计 四格表资料 McNemar'sχ^(2)检验 金标准 SAS软件 R软件 

分 类 号：R195.1[医药卫生—卫生统计学]