Direct Bayesian Additive Regression Trees for Conditional Average Treatment Effects in Regression Discontinuity Designs

2026-03-04

AI Summary

This study addresses the inadequate modeling of treatment effect heterogeneity in regression discontinuity designs when covariates are ignored. To overcome this limitation, the authors propose a nonparametric approach based on Bayesian Additive Regression Trees (BART). The method constructs local linear models within a neighborhood of the cutoff and integrates a generalized Bayesian framework with the Hyvärinen score to automatically select the optimal bandwidth, enabling direct estimation of covariate-dependent conditional average treatment effects. By innovatively combining BART’s flexible nonlinear modeling capabilities with the causal identification structure inherent in regression discontinuity designs, the approach effectively captures complex patterns of heterogeneity. Numerical experiments demonstrate that the proposed method substantially improves the accuracy and robustness of causal effect estimation.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Regression discontinuity designs (RDD) are widely used for causal inference. In many empirical applications, treatment effects vary substantially with covariates, and ignoring such heterogeneity can lead to misleading conclusions, which motivates flexible modeling of heterogeneous treatment effects in RDD. To this end, we propose a Bayesian nonparametric approach to estimating heterogeneous treatment effects based on Bayesian Additive Regression Trees (BART). The key feature of our method lies in adopting a general Bayesian framework using a pseudo-model defined through a loss function for fitting local linear models around the cutoff, which gives direct modeling of heterogeneous treatment effects by BART. Optimal selection of the bandwidth parameter for the local model is implemented using the Hyvärinen score. Through numerical experiments, we demonstrate that the proposed approach flexibly captures complicated structures of heterogeneous treatment effects as a function of covariates.

Problem

• Regression Discontinuity Designs
• Heterogeneous Treatment Effects
• Causal Inference
• Bayesian Nonparametrics

Innovation

• Bayesian Additive Regression Trees
• Regression Discontinuity Design
• Heterogeneous Treatment Effects
• General Bayesian Framework
• Hyvärinen Score