Marginally Specified Hierarchical Models for Networks and Relational Data: An Application to Health Policy

• Activity Number: 66
• Type: Topic Contributed
• Date/Time: Sunday, August 1, 2010 : 4:00 PM to 5:50 PM
• Sponsor: Health Policy Statistics Section
• Author(s): Andrew C. Thomas*+ and Joseph Blitzstein
• Companies: Carnegie Mellon University and Harvard University
• Keywords: networks ; bayesian ; MCMC

Abstract

We present a unified approach to modelling dyadic relational data, namely that seen in social, biological and technological networks, without restriction to the binary format. The approach involves three principles: considering the marginal specification of any edge as the fundamental unit, embedding as much dependence as possible in latent structural forms, and using distributional forms that favour high-throughput computational methods for their solution. We show that this approach allows for an extremely flexible and generalizable way of describing the structural properties of relational systems. We demonstrate this on a network of doctors and their patients in a hospital community as a method of predicting future behaviour.