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

arXiv: https://arxiv.org/abs/2603.03819 · HTML: https://mlsanity.com/paper/2603.03819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [A General Framework for Updating Belief Distributions](https://mlsanity.com/paper/1306.6430/) (2013)
- [Discussion on "Bayesian Regression Tree Models for Causal Inference: Regularization, Confounding, and Heterogeneous Effects" by Hahn, Murray and Carvalho](https://mlsanity.com/paper/2108.02836/) (2021)
- [Bayesian model comparison with the Hyv"arinen score: computation and consistency](https://mlsanity.com/paper/1711.00136/) (2017)
- [Adaptation of the Tuning Parameter in General Bayesian Inference with Robust Divergence](https://mlsanity.com/paper/2106.06902/) (2021)
- [Hierarchical Regression Discontinuity Design: Pursuing Subgroup Treatment Effects](https://mlsanity.com/paper/2309.01404/) (2023)
- [Local-Polynomial Estimation for Multivariate Regression Discontinuity Designs](https://mlsanity.com/paper/2402.08941/) (2024)
- [Bayesian analysis of regression discontinuity designs with heterogeneous treatment effects](https://mlsanity.com/paper/2504.10652/) (2025)
- [Discovering Heterogeneous Treatment Effects in Regression Discontinuity Designs](https://mlsanity.com/paper/2106.11640/) (2021)
- [A Bayesian Additive Regression Tree Model for Learning Conditional Average Treatment Effects in Regression Discontinuity Designs](https://mlsanity.com/paper/2503.00326/) (2025)

## Abstract (arXiv)

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 Hyv"arinen score. Through numerical experiments, we demonstrate that the proposed approach flexibly captures complicated structures of heterogeneous treatment effects as a function of covariates.