Causal effects based on distributional distances

Causal effects based on distributional distances
复制标题

基于分布距离的因果效应

DOI:
--
复制
发表时间:
2018
期刊:
arXiv.org
影响因子:
--
通讯作者:
Edward H. Kennedy
Edward H. Kennedy
中科院分区:
--
文献类型:
--
作者:
Kwangho Kim;Jisu Kim;Edward H. Kennedy

文献摘要

参考文献

被引文献

相似文献

我们开发了一种新的框架,用于基于未观察到的反事实分布之间的差异来估计因果效应。在我们的设置中,因果效应是根据不同反事实结果分布之间的$L_1$距离来定义的,而不是结果值的平均差异。与简单的方法比较相比,直接比较反事实的结果分布可以提供更多关于因果关系的细微差别和有价值的信息。我们考虑了单源和多源随机研究以及观察性研究,并分析了所提出的估计量的误差界和渐近性质。在此基础上,给出了未知平均分布距离的置信度区间的构造方法。最后,我们对新方法进行了说明,并在实证研究中验证了它们的有效性。
We develop a novel framework for estimating causal effects based on the discrepancy between unobserved counterfactual distributions. In our setting a causal effect is defined in terms of the $L_1$ distance between different counterfactual outcome distributions, rather than a mean difference in outcome values. Directly comparing counterfactual outcome distributions can provide more nuanced and valuable information about causality than a simple comparison of means. We consider single- and multi-source randomized studies, as well as observational studies, and analyze error bounds and asymptotic properties of the proposed estimators. We further propose methods to construct confidence intervals for the unknown mean distribution distance. Finally, we illustrate the new methods and verify their effectiveness in empirical studies.
DOI: 10.1214/19-aos1835
发表时间: 2020-04-01
影响因子: 4.5
作者:
Westling, Ted;Carone, Marco
通讯作者: Carone, Marco
DOI: 10.1093/biomet/asaa076
发表时间: 2021-06-01
期刊: BIOMETRIKA
影响因子: 2.7
作者:
Nie, X.;Wager, S.
通讯作者: Wager, S.