A Bayesian Mixed Effects Model for Longitudinal Social Network Data-Student Paper Competitions

• Activity Number: 190
• Type: Topic Contributed
• Date/Time: Monday, July 30, 2007 : 2:00 PM to 3:50 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Anton Westveld*+ and Peter D. Hoff
• Companies: Washington University in St. Louis and University of Washington
• Keywords: dyadic data ; relational data ; longitudinal ; social networks ; Bayesian estimation ; regression modeling

Abstract

This paper is concerned with a Bayesian approach to the estimation of models for data that arise from measurements made on pairs of actors, where every ordered pair of a group of actors is potentially measured at regular temporal intervals, resulting in social network data for each point in time (longitudinal social network data). Typically social network data are used to study a key social phenomenon, such as trade between nations, in relation to a set of predictor variables while accounting for and learning about the interconnectivity of the actors. The network and temporal dependencies are both based on Markov structures and are modeled through a random effects approach resulting in a stochastic process defined by a set of stationary covariance matrices. We apply the methodology to two real-world datasets: international trade and militarized interstate disputes.