12  Introduction

This module addresses the practical application of statistical models for networks. It begins with data requirements, moves on to estimation and model assessment, and spends some time on the issues that can arise with model specifications that use dyad-dependent terms. It ends with a final lab – demonstrating how these tools can be used to conduct a principled analysis of an empirical network, that will in turn produce a believable simulation of a network. Simulations from these models provide a solid foundation for epidemic modeling on networks.

12.1 Module Learning Objectives

• Understand how sampled network data can be used to estimate ERGMs and TERGMs, and in particular how egocentrically sampled data can be in this context
• Understand how the MCMC-MLE algorithm works for estimation, and how the same MCMC algorithm is used for goodness-of-fit assessments and network simulation from fitted models
• Learn the basics of diagnosing problems with MCMC performance
• Understand how goodness of fit assessments are used to validate network models by checking against unmodeled network features
• Understand the concept of model degeneracy with dyad-dependent specifications, why it is a form of model misspecification, and how to avoid it
• Develop confidence in model specification, assessment and simulation through hands on lab assignment.

Bottom line, take-away:

• EpiModel relies on a uniquely powerful set of tools for modeling epidemics on networks.
• These leverage the statistical principle of sufficiency to dramatically reduce data requirements.
• And they provide modelers with a solid foundation for simulating networks that reliably reproduce the wide range of patterns observed in real data.