Working Paper: CEPR ID: DP18141
Authors: Arindrajit Dube; Daniele Girardi; Oscar Jorda; Alan Taylor
Abstract: Many of the challenges in the estimation of dynamic heterogeneous treatment effects can be resolved with local projection (LP) estimators of the sort used in applied macroeconometrics. This approach provides a convenient alternative to the more complicated solutions proposed in the recent literature on Difference-in-Differences (DiD). The key is to combine LPs with a flexible ‘clean control’ condition to define appropriate sets of treated and control units. Our proposed LP-DiD estimator is clear, simple, easy and fast to compute, and it is transparent and flexible in its handling of treated and control units. Moreover, it is quite general, including in its ability to control for pre-treatment values of the outcome and of other time-varying covariates. The LP-DiD estimator does not suffer from the negative weighting problem, and indeedcan be implemented with any weighting scheme the investigator desires. Simulations demonstrate the good performance of the LP-DiD estimator in common settings. Two recent empirical applications illustrate how LP-DiD addresses the bias of conventional fixed effects estimators, leading to potentially different results.
Keywords: Difference-in-Differences; Two-way Fixed Effects; Event Study; Negative Weights; Local Projections; Clean Controls
JEL Codes: C01; C10; C21; C22; C23; C31; C33
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| LP DiD estimator (C51) | performs well compared to other estimators (C51) |
| LP DiD estimator (C51) | dynamic heterogeneous treatment effects (C32) |
| clean control condition (Q52) | accurate identification of convex weighted average of heterogeneous cohort-specific treatment effects (C21) |
| treatment variance and subsample size (C32) | weights assigned to treatment effects (C22) |
| LP DiD estimator (C51) | control for pretreatment values and time-varying covariates (C22) |
| LP DiD estimator (C51) | unbiased estimates in contexts with parallel trends assumption (C51) |