Abstract: The synthetic control method (SCM) is a popular approach for estimating the impact of a treatment on a single unit in panel data settings. The "synthetic control" is a weighted average of control units that balances the treated unit's pre-treatment outcomes as closely as possible. A critical feature of the original proposal is to use SCM only when the fit on pre-treatment outcomes is excellent. We propose Augmented SCM as an extension of SCM to settings where such pre-treatment fit is infeasible. Analogous to bias correction for inexact matching, Augmented SCM uses an outcome model to estimate the bias due to imperfect pre-treatment fit and then de-biases the original SCM estimate. Our main proposal, which uses ridge regression as the outcome model, directly controls pre-treatment fit while minimizing extrapolation from the convex hull. This estimator can also be expressed as a solution to a modified synthetic controls problem that allows negative weights on some donor units. We bound the estimation error of this approach under different data generating processes, including a linear factor model, and show how regularization helps to avoid over-fitting to noise. We demonstrate gains from Augmented SCM with extensive simulation studies and apply this framework to estimate the impact of the 2012 Kansas tax cuts on economic growth. We implement the proposed method in the new augsynth R package.
Recommendations
- Statistical inference for average treatment effects estimated by synthetic control methods
- On the Properties of the Synthetic Control Estimator with Many Periods and Many Controls
- Robust synthetic control
- A flexible synthetic control method for modeling policy evaluation
- Prediction Intervals for Synthetic Control Methods
Cites work
- An Exact and Robust Conformal Inference Method for Counterfactual and Synthetic Controls
- Approximate residual balancing: debiased inference of average treatment effects in high dimensions
- Assessing the causal effect of binary interventions from observational panel data with few treated units
- Bias-Corrected Matching Estimators for Average Treatment Effects
- Estimation of Regression Coefficients When Some Regressors Are Not Always Observed
- scientific article; zbMATH DE number 2168212 (Why is no real title available?)
- On the application of probability theory to agricultural experiments. Essay on principles. Section 9. Translated from the Polish and edited by D. M. Dąbrowska and T. P. Speed
- Robust synthetic control
- Statistical inference for average treatment effects estimated by synthetic control methods
Cited in
(36)- Assessing the causal effect of binary interventions from observational panel data with few treated units
- A flexible synthetic control method for modeling policy evaluation
- Treatment effects in interactive fixed effects models with a small number of time periods
- Robust synthetic control
- Statistical inference for average treatment effects estimated by synthetic control methods
- On the Properties of the Synthetic Control Estimator with Many Periods and Many Controls
- A Penalized Synthetic Control Estimator for Disaggregated Data
- Prediction Intervals for Synthetic Control Methods
- The policy is always greener: impact heterogeneity of Covid-19 vaccination lotteries in the US.
- Hospital quality risk standardization via approximate balancing weights
- Estimating the effects of a California gun control program with multitask Gaussian processes
- What's trending in difference-in-differences? A synthesis of the recent econometrics literature
- Varying impacts of letters of recommendation on college admissions
- Balancing weights for region-level analysis: the effect of medicaid expansion on the uninsurance rate among states that did not expand medicaid
- Synthetic learner: model-free inference on treatments over time
- Synthetic Control with Time Varying Coefficients A State Space Approach with Bayesian Shrinkage
- Confidence intervals of treatment effects in panel data models with interactive fixed effects
- An alternative to synthetic control for models with many covariates under sparsity
- Causality in econometrics: choice vs chance
- Synthetic control as online linear regression
- Distributional synthetic controls
- Same root different leaves: time series and cross-sectional methods in panel data
- Matching on noise: finite sample bias in the synthetic control estimator
- The how and why of Bayesian nonparametric causal inference
- Approximate balancing weights for clustered observational study designs
- Benefits and costs of matching prior to a difference in differences analysis when parallel trends does not hold
- On the use of synthetic difference-in-differences approach with (-out) covariates: The case study of Brexit referendum
- Causal models for longitudinal and panel data: a survey
- Doubly robust proximal synthetic controls
- Reducing labour market flexibility: a causal inference study on reform in the Netherlands
- Dynamic treatment effect estimation with interactive fixed effects and short panels
- Quantile control via random forest
- Direct and spillover effects of a new tramway line on the commercial vitality of peripheral streets: a synthetic-control approach
- Indian Buffet process factor model for counterfactual analysis
- Using Penalized Synthetic Controls on Truncated Data: A Case Study on Effect of Marijuana Legalization on Direct Payments to Physicians by Opioid Manufacturers
- Imputation of Counterfactual Outcomes when the Errors are Predictable
This page was built for publication: The Augmented Synthetic Control Method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5881963)
