Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder.

Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder.
复制标题

用未衡量的混杂因素的代理变量识别因果效应。

DOI:
10.1093/biomet/asy038
复制
发表时间:
2018-12
期刊:
影响因子:
2.7
通讯作者:
Tchetgen Tchetgen E
Tchetgen Tchetgen E
中科院分区:
数学2区
文献类型:
--
作者:
Miao W;Geng Z;Tchetgen Tchetgen E

文献摘要

参考文献

被引文献

相似文献

我们考虑一个因果效应,它被一个未观察到的变量混淆,但与观察到的混淆因素的代理变量。我们表明,至少有两个独立的代理变量满足一定的秩条件,因果效应是非参数识别,即使测量误差机制,即,在给定混杂因素的情况下,可能无法识别代理的条件分布。我们的结果推广了基于测量误差机理辨识的辨识策略。当只有一个代理的混杂因素是可用的,或所需的排名条件不满足,我们开发了一个策略来测试零假设没有因果关系的影响。
We consider a causal effect that is confounded by an unobserved variable, but with observed proxy variables of the confounder. We show that, with at least two independent proxy variables satisfying a certain rank condition, the causal effect is nonparametrically identified, even if the measurement error mechanism, i.e., the conditional distribution of the proxies given the confounder, may not be identified. Our result generalizes the identification strategy of that rests on identification of the measurement error mechanism. When only one proxy for the confounder is available, or the required rank condition is not met, we develop a strategy to test the null hypothesis of no causal effect.
DOI: 10.1097/ede.0b013e3181d61eeb
发表时间: 2010-05
期刊: Epidemiology (Cambridge, Mass.)
影响因子: --
作者:
Lipsitch M;Tchetgen Tchetgen E;Cohen T
通讯作者: Cohen T
DOI: 10.1093/biomet/ass054
发表时间: 2013
期刊: Biometrika
影响因子: 2.7
作者:
Ogburn EL;Vanderweele TJ
通讯作者: Vanderweele TJ
DOI: 10.3982/ecta9988
发表时间: 2014-03-01
期刊: ECONOMETRICA
影响因子: 6.1
作者:
Chen, Xiaohong;Chernozhukov, Victor;Newey, Whitney K.
通讯作者: Newey, Whitney K.
DOI: 10.1093/biostatistics/kxr034
发表时间: 2012-07-01
期刊: BIOSTATISTICS
影响因子: 2.1
作者:
Gagnon-Bartsch, Johann A.;Speed, Terence P.
通讯作者: Speed, Terence P.
DOI: 10.2307/2334349
发表时间: 1974-01-01
期刊: BIOMETRIKA
影响因子: 2.7
作者:
GOODMAN, LA
通讯作者: GOODMAN, LA