Bayesian Shrinkage Priors for Penalized Synthetic Control Estimators in the Presence of Spillovers

2025-01-14

AI Summary

Synthetic Control (SC) methods in policy evaluation are susceptible to bias from spillover effects originating from control units geographically proximate to the treated unit. This paper proposes a distance-weighted Bayesian shrinkage prior, the first approach to explicitly incorporate spatial distance information into the SC framework. Through hierarchical Bayesian modeling, it enables spillover-aware dynamic weight learning, adaptively selecting low-spillover-risk control units while preserving both covariate balance and spatial structure—thus achieving an optimal bias-variance trade-off. Unlike simple exclusion of neighboring units—which sacrifices estimation efficiency—our method retains all controls but downweights those prone to spillovers. Simulation results demonstrate a 42% reduction in estimation bias under strong spillover conditions. An empirical application to Philadelphia’s beverage tax shows a statistically significant decline in sugary drink sales at large supermarkets, with no compensatory increase in artificially sweetened beverage sales.

Technology Category

• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Causality
• Machine Learning: Bayesian Learning

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Synthetic control (SC) methods are widely used to evaluate the impact of policy interventions, particularly those targeting specific geographic areas or regions, commonly referred to as units. These methods construct an artificial (synthetic) unit from untreated (control) units, intended to mirror the characteristics of the treated region had the intervention not occurred. While neighboring areas are often chosen as controls due to their assumed similarities with the treated, their proximity can introduce spillovers, where the intervention indirectly affects these controls, biasing the estimates. To address this challenge, we propose a Bayesian SC method with distance-based shrinkage priors, designed to estimate causal effects while accounting for spillovers. Modifying traditional penalization techniques, our approach incorporates a weighted distance function that considers both covariate information and spatial proximity to the treated. Rather than simply excluding nearby controls, this framework data-adaptively selects those less likely to be impacted by spillovers, providing a balance between bias and variance reduction. Through simulation studies, we demonstrate the finite-sample properties of our method under varying levels of spillover. We then apply this approach to evaluate the impact of Philadelphia's beverage tax on the sales of sugar-sweetened and artificially sweetened beverages in mass merchandise stores.

Problem

• Addresses spillover bias in synthetic control causal estimation methods
• Develops Bayesian shrinkage priors to handle contaminated control units
• Balances covariate similarity and spatial distance to reduce bias

Innovation

• Bayesian shrinkage priors penalize synthetic controls
• Utility function combines similarity and spatial distance
• Data-driven selection balances bias-variance tradeoff