发表机构
University of Oxford; LMU Munich; Munich Center for Machine Learning (MCML)（牛津大学; 慕尼黑大学; 慕尼黑机器学习中心（MCML））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出路径特定危害分解框架，将总负面影响比例分解为直接与间接危害，并给出部分识别界限及半参数有效估计器，用于因果中介分析中的危害评估。
AI 中文摘要
设计治疗策略时的一个核心目标通常是“不造成伤害”，即避免那些在改善平均结果的同时却使某些个体结果恶化的干预措施。一个广泛使用的危害概念是负面影响比例（FNA），定义为干预降低个体结果的概率。然而，在许多应用中，治疗通过中介变量起作用，单一的“总”FNA可能掩盖危害究竟主要源于直接路径还是间接（中介诱导）路径。在本工作中，我们引入了FNA的路径特定类比。为此，我们在因果中介设置中将总危害分解为直接危害和间接危害。然而，这些量依赖于潜在结果的联合分布，即使在随机对照试验中也无法点识别。作为补救，我们为直接和间接FNA开发了一个新颖的部分识别框架。在我们的框架中，我们（i）推导了FNA的尖锐Makarov界，以及（ii）在温和的边际条件下，提出了一种半参数有效估计器，为这些界提供有效的置信区间。我们通过多种数值实验展示了我们的框架。据我们所知，我们是首个研究因果危害的路径特定分解并为其分析开发正交推断框架的工作。
英文摘要
A central goal when designing treatment policies is often to "do no harm", that is, to avoid interventions that improve average outcomes while worsening outcomes for some individuals. A widely used notion for harm is the fraction of negatively affected (FNA), defined as the probability that an intervention decreases an individual's outcome. However, in many applications, treatments operate through mediators, and a single "total" FNA can obscure whether harm arises primarily through direct pathways or indirect (mediator-induced) pathways. In this work, we introduce a path-specific analogue of the FNA. For this, we disentangle total harm into direct and indirect harm in causal mediation settings. However, these quantities depend on joint distributions of potential outcomes that are not point-identified even in randomised controlled trials. As a remedy, we develop a novel partial identification framework for direct and indirect FNA. In our framework, we (i) derive sharp Makarov bounds for the FNA, and (ii) propose a semiparametrically efficient estimator with valid confidence intervals for these bounds under mild margin conditions. We demonstrate our framework across various numerical experiments. To the best of our knowledge, we are the first to study path-specific decomposition of causal harm and to develop an orthogonal inference framework for its analysis.
