基于中位数的因果树与因果森林分裂准则
Median-based Splitting Rules for Causal Trees and Forests
浏览论文内容
中文总结 AI 辅助
针对重尾和偏态结果，提出基于中位数的分裂准则（MSD），在因果树/森林中替代均方误差，提升条件平均处理效应估计的稳健性，并通过模拟和两个实证应用验证。
中文摘要 AI 辅助
在用于估计异质性处理效应的随机实验和观察性研究中，重尾和偏态结果变量很常见，然而指导诚实因果树分裂的均方误差准则对这些极端值很敏感。基于因果森林框架（Athey 和 Imbens, 2016；Wager 和 Athey, 2018），我们引入了中位数平方偏差（MSD）准则，该准则在诚实分裂目标中用 Hodges-Lehmann 位置估计量替代叶均值差，同时保持诚实的叶估计和森林推断不变。另外两个基于中位数的准则，即中位数绝对偏差（MAD）和最小中位数平方（LMS），作为稳健的基线。我们在一个涵盖精度、偏差和置信区间覆盖率的模拟研究中评估了这些准则。MSD 将其稳健性限制在分裂选择上，并降低了在重尾和偏态结果下条件平均处理效应估计的误差。此外，我们重新审视了两个实证应用：第一个分析了墨西哥有条件现金转移项目对选区层面观察数据的选举效应，第二个应用研究了 HIV 阳性成人中的抗逆转录病毒治疗。
英文摘要
Heavy-tailed and skewed outcomes are common in the randomized experiments and observational studies used to estimate heterogeneous treatment effects, yet the mean-squared-error criterion that guides splitting in honest causal trees is sensitive to the extreme values they generate. Building on the causal forest framework (Athey and Imbens, 2016; Wager and Athey, 2018), we introduce the Median Squared Deviation (MSD) criterion, which replaces the leafwise difference in means in the honest splitting objective with the Hodges--Lehmann location estimator while leaving honest leaf estimation and forest inference unchanged. Two further median-based rules, the Median Absolute Deviation (MAD) and the Least Median of Squares (LMS), serve as robust baselines. We evaluate the criteria in a simulation study covering precision, bias, and confidence interval coverage. MSD restricts its robustness to split selection and lowers the error of conditional average treatment effect estimates under heavy-tailed and skewed outcomes. Further, we re-visit two empirical applications: the first analyzes the electoral effects of a Mexican conditional cash transfer program on precinct-level observations, while the second application studies antiretroviral treatments in HIV-positive adults.
发表机构
- University of Duisburg-Essen（杜伊斯堡-埃森大学）
- Ruhr Graduate School in Economics (RGS Econ)（鲁尔经济学研究生院）
- Research Academy Ruhr（鲁尔研究学院）
机构由 AI 辅助整理，请以论文原文为准。
