Estimating spillovers using imprecisely measured networks

TL;DR

This paper addresses the challenge of estimating treatment effects in networks with noisy or imprecise measurements, proposing a new mixture model-based method that improves robustness over existing approaches.

Contribution

It introduces a novel mixture model approach with an EM algorithm to correct for measurement errors in network data for treatment effect estimation.

Findings

The new method reduces bias caused by network mismeasurement.

Simulation results demonstrate improved accuracy over traditional methods.

Application to real data shows increased robustness of estimates.

Abstract

In many experimental contexts, whether and how network interactions impact the outcome of interest for both treated and untreated individuals are key concerns. Networks data is often assumed to perfectly represent these possible interactions. This paper considers the problem of estimating treatment effects when measured connections are, instead, a noisy representation of the true spillover pathways. We show that existing methods, using the potential outcomes framework, yield biased estimators in the presence of this mismeasurement. We develop a new method, using a class of mixture models, that can account for missing connections and discuss its estimation via the Expectation-Maximization algorithm. We check our method's performance by simulating experiments on real network data from 43 villages in India. Finally, we use data from a previously published study to show that estimates using our method are more robust to the choice of network measure.