Large-Sample Properties of the Synthetic Control Method under Selection on Unobservables
Preprint
Abstract
We analyze the synthetic control (SC) method in panel data settings with many units. We assume the treatment assignment is based on unobserved heterogeneity and pre-treatment information, allowing for both strictly and sequentially exogenous assignment processes. We show that the critical property that determines the behavior of the SC method is the ability of input features to approximate the unobserved heterogeneity. Our results imply that the SC method delivers asymptotically normal estimators for a large class of linear panel data models as long as the number of pre-treatment periods is sufficiently large, making it a natural alternative to the Difference-in-Differences.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- Design-Based Uncertainty for Quasi-ExperimentsJournal of the American Statistical Association, 2025
- Linear panel regressions with two-way unobserved heterogeneityJournal of Econometrics, 2023
- Factor and Factor Loading Augmented Estimators for Panel Regression With Possibly Nonstrong FactorsJournal of Business & Economic Statistics, 2022
- Estimating dynamic treatment effects in event studies with heterogeneous treatment effectsJournal of Econometrics, 2021
- The Augmented Synthetic Control MethodJournal of the American Statistical Association, 2021
- An Exact and Robust Conformal Inference Method for Counterfactual and Synthetic ControlsJournal of the American Statistical Association, 2021
- Face masks considerably reduce COVID-19 cases in GermanyProceedings of the National Academy of Sciences, 2020
- Individual effects and dynamics in count data modelsJournal of Econometrics, 2002
- Initial conditions and moment restrictions in dynamic panel data modelsJournal of Econometrics, 1998
- Multivariate regression models for panel dataJournal of Econometrics, 1982