Relative Bias Under Imperfect Identification in Observational Causal Inference

2025-07-31

AI Summary

This paper addresses the practical challenge in observational causal inference where identification assumptions are often violated. It systematically examines bias properties of three mainstream approaches—observable covariate adjustment, instrumental variable (IV) methods, and proximal causal inference—under assumption violations. Through rigorous mathematical derivation, it establishes, for the first time, a unified characterization of bias amplification: both IV and proximal methods exhibit heightened sensitivity to unobserved confounding, magnified by residual confounding in the outcome. The paper proposes a general sensitivity analysis framework and introduces enhanced bias contour plots to visually characterize trade-offs among identification strategies, revealing that method selection implicitly encodes prior beliefs about the degree of violation of assumptions underlying alternative approaches. Reanalysis of Polish surveillance and protest data empirically confirms substantial heterogeneity in sensitivity to assumption deviations across methods.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Knowledge Representation and Reasoning: Preferences

Application Category

• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

To conduct causal inference in observational settings, researchers must rely on certain identifying assumptions. In practice, these assumptions are unlikely to hold exactly. This paper considers the bias of selection-on-observables, instrumental variables, and proximal inference estimates under violations of their identifying assumptions. We develop bias expressions for IV and proximal inference that show how violations of their respective assumptions are amplified by any unmeasured confounding in the outcome variable. We propose a set of sensitivity tools that quantify the sensitivity of different identification strategies, and an augmented bias contour plot visualizes the relationship between these strategies. We argue that the act of choosing an identification strategy implicitly expresses a belief about the degree of violations that must be present in alternative identification strategies. Even when researchers intend to conduct an IV or proximal analysis, a sensitivity analysis comparing different identification strategies can help to better understand the implications of each set of assumptions. Throughout, we compare the different approaches on a re-analysis of the impact of state surveillance on the incidence of protest in Communist Poland.

Problem

• Analyzes bias in causal inference under imperfect assumptions
• Compares sensitivity of identification strategies to violations
• Evaluates impact of state surveillance on protest incidence

Innovation

• Develops bias expressions for IV and proximal inference
• Proposes sensitivity tools for identification strategies
• Uses augmented bias contour plot for visualization