Homophily-adjusted social influence estimation

TL;DR

This paper introduces a novel homophily-adjusted social influence model that accurately estimates social influence from cross-sectional data by accounting for latent homophilic features, improving upon traditional models like NAM.

Contribution

The study provides the first sufficient conditions for estimating social influence from cross-sectional data and proposes a new model that adjusts for latent homophily, extending existing methods.

Findings

The proposed model outperforms the conventional NAM in simulations.

NAM is only valid when all homophilic attributes are observed.

The model effectively disentangles social influence from homophily effects.

Abstract

Homophily and social influence are two key concepts of social network analysis. Distinguishing between these phenomena is difficult, and approaches to disambiguate the two have been primarily limited to longitudinal data analyses. In this study, we provide sufficient conditions for valid estimation of social influence through cross-sectional data, leading to a novel homophily-adjusted social influence model which addresses the backdoor pathway of latent homophilic features. The oft-used network autocorrelation model (NAM) is the special case of our proposed model with no latent homophily, suggesting that the NAM is only valid when all homophilic attributes are observed. We conducted an extensive simulation study to evaluate the performance of our proposed homophily-adjusted model, comparing its results with those from the conventional NAM. Our findings shed light on the nuanced dynamics of social networks, presenting a valuable tool for researchers seeking to estimate the effects of social influence while accounting for homophily. Code to implement our approach is available at https://github.com/hanhtdpham/hanam.