倾向评分逆处理概率加权在生存分析中的应用及SAS宏实现  

Applying the method of inverse probability of treatment weighting based on propensity score in survival analysis and implementing it using SAS macro

作　　者：涂娇[1] 陈卉[1] 倪平[1] 齐潇[1] 肖婉[1] 许林勇[1,2] 

机构地区：[1]中南大学公共卫生学院卫生统计学教研室 [2]中南大学湘雅三医院药物临床研究统计分析中心

出　　处：《中国临床药理学与治疗学》2015年第9期1011-1019,共9页Chinese Journal of Clinical Pharmacology and Therapeutics

摘　　要：目的:探讨基于倾向性评分(propensity score,PS)的逆处理概率加权(inverse probability of treatment weighting,IPTW)法在观察性生存研究数据分析中的应用,并用SAS宏实现该过程。方法:根据基于PS的IPTW法的原理和分析步骤及加权样本中生存分析的相关统计量的计算公式,编写SAS宏命令。结果:编写的SAS宏能够实现使用基于PS的IPTW法对基线不均衡的生存研究数据进行分析,并输出所需的统计量及假设检验P值。结论:基线不均衡的观察性生存研究数据应该采用基于PS的IPTW法,SAS宏为此法提供了方便,节省了研究者统计分析时间,有助于其推广使用。AIM： To explore the application of the method of inverse probability of treatment weighting（ IPTW） based on propensity score（ PS） in survival analysis,and implement it using SAS macro. METHODS： Wrote the SAS macro code on the basis of the principle and analysis procedure of the method,and calculation formula of related statistics in survival analysis in weighted sample. RESULTS：The SAS macro was able to use the method of IPTW based on PS to analyze the survival data with baseline imbalance,and output the required statistics and P value of hypothesis test. CONCLUSION：Observational survival data with baseline imbalance should adopt the method of IPTW based on PS,and SAS macro provide great convenience to implement the method,thus saving much time on statistical analysis and contributing to the popularization and application of the method.

关 键 词：生存分析 逆处理概率加权 倾向评分 

分 类 号：R311[医药卫生—基础医学]