发表机构
Royal College of Surgeons in Ireland (RCSI University of Medicine and Health Sciences)（爱尔兰皇家外科医学院（RCSI 医学与健康科学大学））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出阶乘多元贝叶斯因果森林，统一估计多个二元处理对相关结果的异质主效应与交互效应，提供高效采样与可解释性工具，模拟验证稳健，并应用于多领域数据。
AI 中文摘要
许多研究同时将单元暴露于多个二元处理，并记录多个相关结果，然而分析人员通常一次仅估计一个处理对一个结果的平均效应——忽略了处理间的交互作用以及效应在不同单元间的异质性。我们引入了阶乘多元贝叶斯因果森林，这是一种贝叶斯非参数模型，它将处理格上的阶乘响应面分解为一个预后树和（每个主效应或交互效应各一个）树和，每个树和具有相关的多元叶参数，并以连贯的不确定性联合估计。一个单一的指示器加权核采样所有组件——预后项是指示器为1的特殊情况——因此双处理模型、单处理多元因果森林以及一般的r阶截断是同一个采样器。我们给出了每个估计量的ANOVA/Möbius识别、一个高效的Rcpp引擎，以及一个使用值抑制不确定性图的可解释性层。在模拟中，平均效应估计量是无偏的，具有名义覆盖率，一致且在错误设定下稳健，仅在未测量的混杂下失败，我们对此进行了标记。我们在临床、农业和经济数据以及NHANES调查的更深层次应用中展示了该方法。软件以R包形式提供。
英文摘要
Many studies expose units to several binary treatments at once and record several correlated outcomes, yet analysts usually estimate one treatment's average effect on one outcome at a time -- discarding how treatments interact and how their effects vary across units. We introduce the factorial multivariate Bayesian causal forest, a Bayesian nonparametric model that decomposes the factorial response surface over the treatment lattice into a prognostic sum-of-trees plus one sum-of-trees per main or interaction effect, each with correlated multivariate leaf parameters, estimated jointly with coherent uncertainty. A single indicator-weighted kernel samples every component -- the prognostic term is the special case whose indicator is unity -- so the two-treatment model, the single-treatment multivariate causal forest, and a general order-r truncation are one and the same sampler. We give the ANOVA/Möbius identification of each estimand, an efficient Rcpp engine, and an interpretability layer using value-suppressing uncertainty maps. In simulations the average-effect estimators are unbiased with nominal coverage, consistent, and robust under misspecification, failing only under unmeasured confounding, which we flag. We illustrate the method on clinical, agricultural and economic data and on a deeper application to the NHANES survey. Software is provided as an R package.
Comments31 pages. Accompanying R package: mvbcfMT
