Estimation and inference for causal spillover effects in egocentric-network randomized trials in the presence of network membership misclassification

TL;DR

This paper develops methods to accurately estimate spillover effects in egocentric-network randomized trials despite network misclassification, which is crucial for evaluating interventions like HIV prevention strategies.

Contribution

It introduces a bias correction approach combining measurement error and causal inference techniques for network misclassification in ENRTs with validation data.

Findings

Methods effectively reduce bias in spillover effect estimates.

Simulation studies demonstrate good finite-sample performance.

Application to HIV study illustrates practical utility.

Abstract

To leverage peer influence and increase population behavioral changes, behavioral interventions often rely on peer-based strategies. A common study design that assesses such strategies is the egocentric-network randomized trial (ENRT), in which those receiving the intervention are encouraged to disseminate information to their peers. The Average Spillover Effect (ASpE) measures the impact of the intervention on participants who do not receive it, but whose outcomes may be affected by others who do. The assessment of the ASpE relies on assumptions about, and correct measurement of, interference sets within which individuals may influence one another's outcomes. It can be challenging to properly specify interference sets, such as networks in ENRTs, and when mismeasured, intervention effects estimated by existing methods will be biased. In HIV prevention studies where social networks play an important role in disease transmission, correcting ASpE estimates for bias due to network misclassification is critical for accurately evaluating the full impact of interventions. We combined measurement error and causal inference methods to bias-correct the ASpE estimate for network misclassification in ENRTs, when surrogate networks are recorded in place of true ones, and validation data that relate the misclassified to the true networks are available. We investigated finite sample properties of our methods in an extensive simulation study, and illustrated our methods in the HIV Prevention Trials Network (HPTN) 037 study.