Bayesian Analysis of Social Influence

TL;DR

This paper develops a comprehensive Bayesian inference framework for the auto logistic actor-attribute model (ALAAM), enabling testing of dependencies and handling missing data, demonstrated through three diverse empirical social network examples.

Contribution

It introduces a new Bayesian inference scheme for ALAAMs that supports dependency testing and missing data management, advancing social network analysis methods.

Findings

Effective testing of dependencies across data subsets

Successful handling of missing data in social network models

Empirical validation across three social contexts

Abstract

The network influence model is a model for binary outcome variables that accounts for dependencies between outcomes for units that are relationally tied. The basic influence model was previously extended to afford a suite of new dependence assumptions and because of its relation to traditional Markov random field models it is often referred to as the auto logistic actor-attribute model (ALAAM). We extend on current approaches for fitting ALAAMs by presenting a comprehensive Bayesian inference scheme that supports testing of dependencies across subsets of data and the presence of missing data. We illustrate different aspects of the procedures through three empirical examples: masculinity attitudes in an all-male Australian school class, educational progression in Swedish schools, and un-employment among adults in a community sample in Australia.