A Way to Synthetic Triple Difference

TL;DR

This paper introduces a method combining synthetic control with triple difference to improve causal inference when the parallel trends assumption is violated, enhancing robustness in policy evaluation studies.

Contribution

It presents a novel approach that transforms triple difference into a DID structure, allowing synthetic control methods to be applied in more complex causal inference scenarios.

Findings

Effective in addressing violations of parallel trends

Applied to real-world data demonstrating practical utility

Provides guidelines and cautions for implementation

Abstract

This paper discusses a practical approach that combines synthetic control with triple difference to address violations of the parallel trends assumption. By transforming triple difference into a DID structure, we can apply synthetic control to a triple-difference framework, enabling more robust estimates when parallel trends are violated across multiple dimensions. The proposed procedure is applied to a real-world dataset to illustrate when and how we should apply this practice, while cautions are presented afterwards. This method contributes to improving causal inference in policy evaluations and offers a valuable tool for researchers dealing with heterogeneous treatment effects across subgroups.