Doubly robust local projections difference-in-differences
Daniel de Abreu Pereira Uhr, Guilherme Valle Moura
TLDR
DRLPDID is a new doubly robust local-projections difference-in-differences estimator for staggered treatments, offering consistent estimation and robust inference.
Key contributions
- Introduces DRLPDID, a doubly robust LP-DiD estimator for staggered absorbing treatments.
- Ensures consistency if either the outcome regression or treatment probability model is correctly specified.
- Provides influence-function-based inference and multiplier-bootstrap bands for dynamic paths.
- Outperforms IPT-only variants under propensity-score misspecification in Monte Carlo simulations.
Why it matters
This paper significantly enhances the robustness of causal inference in staggered difference-in-differences settings. Its doubly robust nature provides more reliable estimates, even with model misspecification. This is crucial for accurate policy evaluation.
Original Abstract
This paper develops a doubly robust extension of local-projections difference-in-differences (LP-DiD) for staggered absorbing treatments. The resulting estimator, DRLPDID, preserves the LP-DiD local-stack ATT target and is consistent when either the local untreated-outcome regression or the local treatment-probability model is correctly specified. It also delivers influence-function-based inference for post-treatment summaries and multiplier-bootstrap bands for dynamic paths. In Monte Carlo designs with covariate-driven selection, DRLPDID matches regression-adjusted LP-DiD under outcome-model alignment and clearly outperforms the IPT-only variant under propensity-score misspecification. In the no-fault-divorce application, DRLPDID tracks robust staggered-adoption estimators and is less negative than unadjusted LP-DiD.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.