Causal inference with dyadic data in randomized experiments

2025-05-27

AI Summary

This paper addresses causal inference for binary networked data—such as pairwise user interactions—where traditional individual-level randomized experiments suffer from bias due to network interference. We propose the first design-driven causal inference framework specifically tailored for binary outcomes. Our method rigorously constructs an unbiased estimator for the global average treatment effect (GATE) and, leveraging randomization design and asymptotic statistical theory, establishes its asymptotic normality along with a consistent variance estimator. A key innovation lies in explicitly modeling the interference structure and adjusting the variance estimation accordingly, thereby substantially improving estimation accuracy and inferential reliability. The framework is validated on large-scale online experiments conducted on WeChat Channels, where it accurately quantifies the causal impact of recommendation algorithms on pairwise user interaction metrics.

Technology Category

Reasoning under Uncertainty: CausalityMachine Learning: Causal LearningMultiagent Systems: Mechanism Design

Application Category

Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystemsResponsible Web: Human-perceived consequences of algorithmic deployment on the webGraph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Estimating the treatment effect within network structures is a key focus in online controlled experiments, particularly for social media platforms. We investigate a scenario where the unit-level outcome of interest comprises a series of dyadic outcomes, which is pervasive in many social network sources, spanning from microscale point-to-point messaging to macroscale international trades. Dyadic outcomes are of particular interest in online controlled experiments, capturing pairwise interactions as basic units for analysis. The dyadic nature of the data induces interference, as treatment assigned to one unit may affect outcomes involving connected pairs. We propose a novel design-based causal inference framework for dyadic outcomes in randomized experiments, develop estimators of the global average causal effect, and establish their asymptotic properties under different randomization designs. We prove the central limit theorem for the estimators and propose variance estimators to quantify the estimation uncertainty. The advantages of integrating dyadic data in randomized experiments are manifested in a variety of numerical experiments, especially in correcting interference bias. We implement our proposed method in a large-scale experiment on WeChat Channels, assessing the impact of a recommendation algorithm on users' interaction metrics.

Problem

• Estimating treatment effects in network-structured dyadic data
• Addressing interference bias in randomized social media experiments
• Developing causal inference for pairwise interaction outcomes

Innovation

• Design-based causal inference for dyadic outcomes
• Estimators for global average causal effect
• Variance estimators for quantification uncertainty