We propose a novel Bayesian methodology to mitigate misspecification and improve estimating treatment effects. A plethora of methods to estimate -- particularly the heterogeneous -- treatment effect have been proposed with varying success. It is recognized, however, that the underlying data generating mechanism, or even the model specification, can drastically affect the performance of each method, without any way to compare its performance in real world applications. Using a foundational Bayesian framework, we develop Bayesian causal synthesis; a supra-inference method that synthesizes several causal estimates to improve inference. We provide a fast posterior computation algorithm and show that the proposed method provides consistent estimates of the heterogeneous treatment effect. Several simulations and an empirical study highlight the efficacy of the proposed approach compared to existing methodologies, providing improved point and density estimation of the heterogeneous treatment effect.

翻译：我们提出了一种新颖的贝叶斯方法，旨在缓解模型设定错误并改进处理效应的估计效果。现有大量用于估计——特别是异质性——处理效应的方法已取得不同程度的成功，然而人们认识到，底层数据生成机制乃至模型规范会显著影响每种方法的性能，而实际应用中却缺乏评估其性能的手段。基于基础贝叶斯框架，我们发展了贝叶斯因果合成方法；这是一种超推断技术，通过综合多种因果估计值来改进推断效果。我们提出了快速后验计算算法，并证明该方法能对异质性处理效应提供一致估计。通过多项仿真实验与实证研究，相较于现有方法，本文方法在异质性处理效应的点估计与密度估计方面均展现出更优性能。