ERGM 1 and 2

Instructor: Eric Quintane

ERGMs (exponential random graph models) are statistical models that predict the presence/absence of ties. Essentially, they view an observed network as the outcome of a set of forces that make specific micro-configurations (e.g., a closed triad) more or less likely.

In the first ERGM mini module, participants will gain an intuitive (i.e., no stats and no data) understanding of why, and when, ERGMs are appropriate tools to model social networks, what ERGMs can do, and what they cannot do. The mini module will explain the theoretical foundations of ERG modeling, introduce dependence assumptions and describe the network configurations typically used in ERGMs.

In the second ERGM mini module, participants will learn the typical process used to specify, estimate, evaluate and interpret an ERGM, using a empirical example. The empirical example will cover network configurations for one mode directed network with actor attributes and network covariates.

After attending the two modules, participants should have gained sufficient criteria to evaluate the use of ERGMs from a theoretical, methodological and empirical perspective when reviewing an article.