均衡组间差异的有效方法:倾向评分

目的：实例介绍倾向评分法的基本原理和适用条件，设计适用于分析二分类资料的SAS宏程序。方法：运用倾向评分比较平衡前后两组间差异的改变情况，评价放弃心肺复苏急救与充血性心力衰竭患者院内死亡的联系。结果：采用分层法和匹配法都可以有效地平衡两组各个特征变量间所存在的高度差异，三种分析方法获得相近的估计结果。结论：倾向评分法是均衡组间差异的有效方法，能够匹配和平衡各个特征变量的作用，并用于分析各种观察性研究资料。

An effective method to reduce bias between two compared groups: propensity score

Objective Through introduction of principal theory and algorithm of propensity score to design SAS macro programs for binary data. Methods Propensity score method was used to compare the differences of character variables between two groups, and the association of DNR (Do Not Resuscitate) with the mortality of congestive heart failure was evaluated with different methods. Results Significant differences among the character variables between two groups were effectively balanced with stratification or matching method. The odds ratios of DNR with the in-hospital mortality rate of congestive heart failure were estimated identical with different algorithms and to find that the association of DNR to in-hospital mortality was highly significant. Conclusion Propensity score was a good algorithm that could be used to analyze any kind of observational data for matching the effects among the character variables.