Path-specific harm decomposition: A partial identification framework

2026-09-24

AI Summary

This study addresses the challenge in causal mediation analysis where total harm often obscures the specific sources of detriment along direct and indirect pathways. To overcome this, the work proposes the first path-specific harm decomposition framework that decouples total harm into its direct and indirect components. Furthermore, it constructs an orthogonalized inference framework integrating partial identification, Makarov bounds, and semiparametric efficient estimation techniques to solve the resulting problem. The primary contributions include deriving sharp identification bounds for the target estimands and providing valid confidence intervals with double robustness properties. Numerical experiments confirm both the theoretical validity and practical effectiveness of the proposed methodology.

Abstract

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.

Innovation

• path-specific harm decomposition
• partial identification
• causal mediation
• Makarov bounds
• semiparametrically efficient estimator