倾向指数匹配法与Logistic回归分析方法对比研究  

COMPARISON OF PROPENSITY SCORE MATCHING AND LOGISTIC REGRESSION

作　　者：王永吉[1] 蔡宏伟[2] 夏结来[1] 蒋志伟[1] 王陵[1] 

机构地区：[1]第四军医大学预防医学系卫生统计学教研室,西安710032 [2]第四军医大学口腔医学院信息中心

出　　处：《现代预防医学》2011年第12期2217-2219,共3页Modern Preventive Medicine

基　　金：国家自然科学基金资助课题;基于HIS的多分组临床观察数据倾向指数匹配的医学循证研究(30800952)

摘　　要：[目的]比较倾向指数匹配法与Logistic回归分析方法的检验效能和I类错误。[方法]通过Monte Carlo模拟比较倾向指数匹配法和Logistic回归处理二分类资料的区别。[结果]倾向指数匹配法和Logistic回归的I类错误无差异,倾向指数全匹配法的检验效能略高。[结论]在观察性研究中,倾向指数匹配法具有很高的实用价值。[Objective]To compare the statistical power and Type I error rates between propensity score and Logistic regression.[Methods]Monte Carlo simulations were adopted to compare the propensity score matching and Logistic regression when they were used to analyze nominal data.[Results]There was no difference between propensity score matching and Logistic regression in Type I error rates.The nearest available neighbor matching had higher power than other methods.[Conclusion]Propensity score matching should be recommended in practice of observational studies.

关 键 词：倾向指数 匹配 LOGISTIC回归 MONTE CARLO模拟 

分 类 号：R195.1[医药卫生—卫生统计学]