大家可以参阅印地安那大学的这个网页关于【倾向得分匹配】方法的介绍:
In Stata, how do I perform propensity score matching?
里面推荐了以下三个用户编写的程序:
psmatch2.ado
pscore.ado
nnmatch.ado
我在这里粗略翻译一下:
In Stata, how do I perform propensity score matching?
在Stata中,我如何实施倾向得分匹配法?
Stata does not have a built-in command for propensityscore matching, a non-experimental method of sampling that produces acontrol group whose distribution of covariates is similar to that ofthe treated group. However, there are several user-written modules forthis method. The following modules are among the most popular:
Stata没有内置的命令来实施倾向得分匹配法,这是一种非实验性抽样方法:它生成一个控制组(对照组),该组的协变量分布类似于诊疗组。不过,有若干用户编写的模块来执行这一方法。下述模块是其中最流行的:
psmatch2.ado
pscore.ado
nnmatch.ado
psmatch2.ado was developed by Leuven and Sianesi (2003)and
pscore.ado by Becker and Ichino (2002). Morerecently, Abadie, Drukker, Herr, and Imbens (2004) introduced
nnmatch.ado. All three modules support pair-matching aswell as subclassification.
【psmatch2.ado】 由Leuven和Sianesi(2003)开发,而【
pscore.ado】由Becker和Ichino(2002)开发。较新近地,是Abadie等(2004)引入的【
nnmatch.ado】。所有这三个模型都支持配对和子分类。
You can find these modules using the
.net command as follows:
你能够使用如下【
.net】命令来找到这些模块:
.net search psmatch2 // 经测试,在Stata12中,只需直接在stata命令窗口中输入 search+模块名称(比如pscore)即可
.net search pscore // st0026_2 中的模块包应该是较新的,其中包含了pscore.ado
.net search nnmatch
You can install these modules using the
.ssc or
.net command, for example:
你可以用【
.ssc】或【
.net】命令来安装这些模块,比如:
.ssc install psmatch2, replace
楼主补充:pscore模块是包含在st0026_2 中的,可使用如下命令:
.net install st0026_2.pkg, replace
After installation, read the help files to find the correct usage, forexample:
在安装完成后,阅读帮助文件以找到正确的使用方法,例如:
.help psmatch2
If you have questions about using statistical and mathematicalsoftware at Indiana University,
email UITSResearch Analytics (formerly known as the Stat/MathCenter). Research Analytics is located on the IU Bloomington campus atWoodburn Hall 200, and is open for consultation by appointmentMonday-Friday 9am-5pm. For more, visit
ResearchAnalytics on the web, or call 812-855-4724 (IUB) or 317-278-4740(IUPUI).
This is document
avll in domain
all.
Last modified on
August 02, 2013.
还可参见:
【倾向得分匹配法(PSM)举例及stata实现】
https://bbs.pinggu.org/thread-1490982-1-1.html
【The Stata Journal Volume 8 Number 4: pp. 532-539】Erratum and discussion of propensity–score reweighting
【The Stata Journal Volume 7 Number 4: pp. 507-541】Causal inference with observational data
补充01:根据二楼坛友的提醒,stata13中已有官方的propensity score matching的命令。
在网上查了一下,是在stata13的手册[TE] Treatment Effects 中的命令 teffects psmatch
不过,根据
re: st: Propensity Score Matching command in Stata 13
官方的-psmatch- 命令和用户编写的命令 -psmatch2- 在功能上还是有差别的,简单的说,-psmatch2- 的灵活度要大一些,详细的情形请参看上述链接。