【AEW Webinar】Two-way Fixed Effects and Differences-in-Differences Estimators in Heterogeneous Adoption Designs

---

• 研討會日期 : 2025-04-10
• 時間 : 15:00
• 主講人 : Professor Xavier D'Haultfoeuille
• 地點 : Register and join online
• 演講者簡介 : Professor Xavier D'Haultfoeuille received his Ph.D. in Economics from Paris I and CREST in 2009. He is currently a Professor at the CREST-ENSAE. His research interests are Econometric Theory and Empirical Industrial Organization.
• 演講摘要 : We consider treatment-effect estimation under a parallel trends assumption, in designs where no unit is treated at period one, all units receive a strictly positive dose at period two, and the dose varies across units. There are therefore no true control groups in such cases. First, we develop a test of the assumption that the treatment effect is mean independent of the treatment, under which the commonly-used two-way-fixed-effects estimator is consistent. When this test is rejected or lacks power, we propose alternative estimators, robust to heterogeneous effects. If there are units with a period-two treatment arbitrarily close to zero, the robust estimator is a difference-in-difference using units with a period-two treatment below a bandwidth as controls. Without such units, we propose non-parametric bounds, and an estimator relying on a parametric specification of treatment-effect heterogeneity. We use our results to revisit Pierce and Schott (2016) and Enikolopov et al. (2011).
• Working Paper Title : Estimating Treatment Effects in Panel Data Without Parallel Trends
• Working Paper Speaker : Professor Shoya Ishimaru
• Working Paper Speaker Biography : Professor Shoya Ishimaru received his Ph.D. in Economics from the University of Wisconsin-Madison in 2020. He is currently an Assistant Professor at Hitotsubashi University. His research interests are Labor Economics, Applied Econometrics, and Economics of Education.
• Working Paper Abstract : This paper proposes a novel approach for estimating treatment effects in panel data settings, addressing key limitations of the standard difference-in-differences (DID) approach. The standard approach relies on the parallel trends assumption, implicitly requiring unobservable factors correlated with treatment assignment to be unidimensional, time-invariant, and affect untreated potential outcomes in an additively separable manner. This paper introduces a more flexible framework that allows for multidimensional unobservables and non-additive separability, and offers sufficient conditions for identifying the average treatment effect on treated. An empirical application to job displacement reveals smaller long-run earnings losses compared to the standard DID approach, reflecting the framework’s ability to account for heterogeneity in earnings growths between treated and control groups. For example, nine years after displacement, the alternative estimate suggests a reduction in earnings less than half of that estimated by the DID approach. While the method requires substantial pre-treatment and post-treatment data and specific conditions on serial correlation, it expands the econometric toolkit by enabling more robust causal inference in the presence of complex unobserved heterogeneity.