Predictive Counterfactuals for Treatment Effect Heterogeneity in Event Studies with Staggered Adoption
Predictive Counterfactuals for Treatment Effect Heterogeneity in Event Studies with Staggered Adoption
复制标题
交错采用事件研究中治疗效果异质性的预测反事实
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Mateus Souza
中科院分区：
文献类型：
--
作者：
Mateus Souza
这篇论文为机器学习应用于因果推理提供了越来越多的文献。我专注于估计治疗效应异质性，特别是治疗/暴露日期随时间变化的事件研究（即交错采用）。最近的计量经济学文献表明，传统的影响评估方法（如固定效应回归）在这些环境中可能存在短期偏差。我介绍了一种方法，不受这种偏见，可以恢复异质性更有效地比标准的固定效应模型。该方法的第一步是通过仅将灵活的机器学习算法应用于预处理数据来准确预测反事实的分布。然后，通过比较反事实和真实结果，可以估计治疗效果的分布。这些影响可以针对样品的不同部分进行总结，从而恢复异质性。通过模拟，我展示了这种方法如何准确和有效，即使在存在动态（随时间变化）的治疗效果。最后，我从美国一个大型住宅能源效率计划的真实的数据的应用。虽然以前的文献仅限于估计平均程序的影响，我确定哪些类型的升级与更高的节能。这些结果提供了有关哪些升级的目标，以提高该计划的成本效益的见解。
This paper contributes to a growing literature on machine learning applications for causal inference. I focus on estimation of treatment effect heterogeneity, specifically for event studies with time-varying treatment/exposure dates (i.e. staggered adoption). Recent econometric literature shows that traditional impact evaluation methods (such as fixed effects regressions) can be near-term biased in those settings. I introduce an approach that does not suffer from such bias, and that can recover heterogeneity more efficiently than standard fixed effects models. The first step of the approach is to accurately predict a distribution of counterfactuals, by applying flexible machine learning algorithms to pre-treatment data only. Then, by comparing counterfactual and true outcomes, it is possible to estimate a distribution of treatment effects. Those effects can be summarized for different portions of the sample, thus recovering heterogeneity. With simulations, I demonstrate how that approach can be accurate and efficient, even in the presence of dynamic (time-varying) treatment effects. I conclude with an application to real data from a large residential energy efficiency program in the US. While prior literature is restricted to estimating average program effects, I identify which types of upgrades are associated with higher energy savings. Those results provide insight about which upgrades to target to improve the program's cost-effectiveness.