Local and Global Optimal Propensity Score Matching
Local and Global Optimal Propensity Score Matching
复制标题
局部和全局最优倾向得分匹配
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
Marcelo Coca
中科院分区：
文献类型：
--
作者：
Marcelo Coca
在观察性研究中，当不可能随机化时，倾向评分匹配方法常用于控制偏倚。本文介绍了如何使用局部和全局最优匹配算法来匹配样本。本文包括宏来执行最近可用的邻居，卡尺和半径匹配方法与或不替换和匹配处理观察到一个或多个控制。观测值之间的相似性使用绝对值和马氏距离来评估，马氏距离包括倾向得分和其他协变量。本文还解释了如何使用网络流找到具有可变数量控制的全局最优匹配。需要安装SAS®9.1、SAS/STAT®和SAS/OR®。
Propensity score-matching methods are often used to control for bias in observational studies when randomization is not possible. This paper describes how to match samples using both local and global optimal matching algorithms. The paper includes macros to perform the nearest available neighbor, caliper, and radius matching methods with or without replacement and matching treated observations to one or many controls. The similarity between observations is evaluated using both the absolute value and the Mahalanobis distance that includes the propensity score along with other covariates. This paper also explains how to find a global optimal match with a variable number of controls using network flows. SAS® 9.1, SAS/STAT®, and SAS/OR® are required.