Policy-relevant causal effect estimation using instrumental variables with interference

2025-09-15

AI Summary

Conventional instrumental variable (IV) methods assume no interference among units, yet real-world policy evaluations frequently involve social interactions that violate this assumption. Method: Under a mild interference assumption, we formally define policy-interpretable direct and spillover effects, and achieve partial identification of these effects under generalized monotonic treatment response and selection assumptions—without imposing parametric restrictions on the interference structure. Our approach integrates IV identification strategies, the potential outcomes framework, and multi-peer interference modeling to derive computationally tractable bounds on causal effects. Contribution/Results: We break the no-interference barrier and provide, for the first time, policy-relevant bounds on causal effects for IV designs with social interactions. This significantly extends the applicability and credibility of IV methods in evaluating real-world social programs—such as education and public health interventions—where peer effects are prevalent.

Technology Category

• Reasoning under Uncertainty: Causality
• Game Theory and Economic Paradigms: Social Choice / Voting
• Machine Learning: Causal Learning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Social and technical mechanisms of refusal for web technologies and applications
• Economics, Online Markets and Human Computation: Social networks and social learning

Abstract

Many policy evaluations using instrumental variable (IV) methods include individuals who interact with each other, potentially violating the standard IV assumptions. This paper defines and partially identifies direct and spillover effects with a clear policy-relevant interpretation under relatively mild assumptions on interference. Our framework accommodates both spillovers from the instrument to treatment and from treatment to outcomes and allows for multiple peers. By generalizing monotone treatment response and selection assumptions, we derive informative bounds on policy-relevant effects without restricting the type or direction of interference. The results extend IV estimation to more realistic social contexts, informing program evaluation and treatment scaling when interference is present.

Problem

• Estimating causal effects with interference in IV methods
• Identifying direct and spillover effects under mild assumptions
• Extending IV estimation to realistic social contexts

Innovation

• Generalizing monotone treatment response assumptions
• Accommodating spillovers from instrument to treatment
• Deriving informative bounds without restricting interference