Forests for Differences: Robust Causal Inference Beyond Parametric DiD

TL;DR

This paper presents DiD-BCF, a new non-parametric Bayesian model for causal inference in difference-in-differences studies, effectively handling heterogeneity, staggered adoption, and complex data structures.

Contribution

Introduces DiD-BCF, a novel non-parametric Bayesian framework that improves causal effect estimation in DiD settings with heterogeneity and non-linearity.

Findings

DiD-BCF outperforms benchmarks in simulations with non-linear effects.

The model uncovers significant heterogeneity in minimum wage effects related to county population.

DiD-BCF enhances estimation accuracy and stability in complex panel data scenarios.

Abstract

This paper introduces the Difference-in-Differences Bayesian Causal Forest (DiD-BCF), a novel non-parametric model addressing key challenges in DiD estimation, such as staggered adoption and heterogeneous treatment effects. DiD-BCF provides a unified framework for estimating Average (ATE), Group-Average (GATE), and Conditional Average Treatment Effects (CATE). A core innovation, its Parallel Trends Assumption (PTA)-based reparameterization, enhances estimation accuracy and stability in complex panel data settings. Extensive simulations demonstrate DiD-BCF's superior performance over established benchmarks, particularly under non-linearity, selection biases, and effect heterogeneity. Applied to U.S. minimum wage policy, the model uncovers significant conditional treatment effect heterogeneity related to county population, insights obscured by traditional methods. DiD-BCF offers a robust and versatile tool for more nuanced causal inference in modern DiD applications.