Doubly robust difference-in-differences estimators
Doubly robust difference-in-differences estimators
复制标题
DOI：
10.1016/j.jeconom.2020.06.003
复制
发表时间：
2020-11-01
影响因子：
6.3
通讯作者：
Zhao, Jun
中科院分区：
文献类型：
--
作者：
Sant'Anna, Pedro H. C.;Zhao, Jun
本文提出了双稳健估计的平均治疗效果的治疗（ATT）在差异中差异（DID）的研究设计。相反，替代DID估计，建议的估计是一致的，如果（但不一定是两者）的倾向得分或结果回归工作模型被正确指定。我们还推导出半参数效率界的KIT在DID设计时，无论是面板或重复的横截面数据，并表明，我们提出的估计达到半参数效率界时，正确指定的工作模型。此外，我们量化了潜在的效率收益，而不是重复的横截面数据的面板数据。最后，通过特别注意的估计方法来估计的滋扰参数，我们表明，有时可以构建双稳健DID估计的ATT，也是双稳健的推理。仿真研究和实证应用说明了所提出的估计理想的有限样本性能。目前已有用于实施拟议政策评价工具的开放源码软件。(C)2020爱思唯尔B.V.保留所有权利。
This article proposes doubly robust estimators for the average treatment effect on the treated (ATT) in difference-in-differences (DID) research designs. In contrast to alternative DID estimators, the proposed estimators are consistent if either (but not necessarily both) a propensity score or outcome regression working models are correctly specified. We also derive the semiparametric efficiency bound for the KIT in DID designs when either panel or repeated cross-section data are available, and show that our proposed estimators attain the semiparametric efficiency bound when the working models are correctly specified. Furthermore, we quantify the potential efficiency gains of having access to panel data instead of repeated cross-section data. Finally, by paying particular attention to the estimation method used to estimate the nuisance parameters, we show that one can sometimes construct doubly robust DID estimators for the ATT that are also doubly robust for inference. Simulation studies and an empirical application illustrate the desirable finite-sample performance of the proposed estimators. Open-source software for implementing the proposed policy evaluation tools is available. (C) 2020 Elsevier B.V. All rights reserved.