Auto-Doubly Robust Estimation of Causal Effects on a Network

2025-06-29

AI Summary

This paper addresses the dual challenges of long-range dependencies and pervasive interference in network causal inference. We propose a novel Network-Enhanced Inverse Probability Weighting (NE-IPW) method, the first to establish a doubly robust identification framework in network settings: it jointly models treatment and outcome mechanisms via chain graph models, introduces a network neighborhood conditional ignorability assumption, and integrates a parametric propensity score model with a semiparametric outcome model. We theoretically prove consistency and asymptotic normality of the estimator. Extensive simulations and empirical analysis—using data from the Brooklyn NNAHRAY study in New York—demonstrate its robustness and efficiency in estimating both direct and spillover effects of incarceration on socioeconomic outcomes. The core contribution is the first formal development of a network-based doubly robust theory, enabling reliable causal effect estimation under long-range dependence.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

This paper develops new methods for causal inference in observational studies on a single large network of interconnected units, addressing two key challenges: long-range dependence among units and the presence of general interference. We introduce a novel network version of Augmented Inverse Propensity Weighted, which combines propensity score and outcome models defined on the network to achieve doubly robust identification and estimation of both direct and spillover causal effects. Under a network version of conditional ignorability, the proposed approach identifies the expected potential outcome for a unit given the treatment assignment vector for its network neighborhood up to a user-specified distance, while marginalizing over treatment assignments for the rest of the network. By introducing two additional assumptions on the outcome, we establish a new doubly robust identification result for the expected potential outcome under a hypothetical intervention on the treatment assignment vector for the entire network. Under a union of Chain Graph models - one governing the propensity model and the other the outcome model - we propose a corresponding semiparametric estimator based on parametric models naturally arising from the chain graph representation of the network. We formally prove that, under weak network dependence, the proposed estimators are asymptotically normal and we characterize the impact of model misspecification on the asymptotic variance. Extensive simulation studies highlight the practical relevance of our approach. We further demonstrate its application in an empirical analysis of the NNAHRAY study, evaluating the impact of incarceration on individual socioeconomic outcomes in Brooklyn, New York.

Problem

• Estimating causal effects in networked observational data
• Addressing long-range dependence and general interference
• Doubly robust identification of direct and spillover effects

Innovation

• Network version of Augmented Inverse Propensity Weighted
• Doubly robust identification for direct and spillover effects
• Semiparametric estimator based on Chain Graph models