4.A.iv The Exponential Random Graph Models (ERGMs) Family of Methods
Exponential Random Graph Models (ERGMs)
🌐 Web Resources
Exponential Random Graph Models (ERGMs) in R for Social Network Analysis
🌐 Link: https://schochastics.github.io/R4SNA/inferential/ergm.html
Termeh Shafie and David Schoch
“Exponential Random Graph Models (ERGMs) provide a flexible way to model these kinds of patterns. Instead of assuming each edge forms independently, ERGMs allow the probability of a tie to depend on what else is happening in the network. For example, the likelihood of a tie forming between two nodes may increase if they share mutual connections (triadic closure), or decrease if one node is already connected to many others (crowding out).
By explicitly modeling such configurations, we gain not only better empirical fit but also the ability to test theoretical hypotheses about the generative processes that shape real-world networks.”
Cross-Sectional Network Models: ERGM in Network Analysis: Integrating Social Network Theory, Method, and Application with R
🌐 Link: https://inarwhal.github.io/NetworkAnalysisR-book/ch13-Cross-Sectional-Network-Models-ERGM-R.html
Craig Rawlings, Jeffrey A. Smith, James Moody, and Daniel McFarland
“This tutorial offers an extended example in R demonstrating how to analyze networks using statistical models. We will focus on exponential-family random graph models (ERGMs). ERGMs are useful as they make it possible to uncover what micro tendencies are important in network formation, comparing rates of reciprocity, homophily (for example) net of other network processes.”
Temporal Exponential Random Graph Models (TERGMs)
Add a Resource Here!
Link: Stand-in Link to Home Page
Authors
Description of the resource here
submitted by YOU!
Separable Temporal Exponential Random Graph Models (STERGMs)
🌐 Web Resources
Longitudinal Network Models: STERGM in Network Analysis: Integrating Social Network Theory, Method, and Application with R
🌐 Link: https://inarwhal.github.io/NetworkAnalysisR-book/ch13-Longitudinal-Network-Models-STERGM-R.html
Craig Rawlings, Jeffrey A. Smith, James Moody, and Daniel McFarland
“This is the second tutorial for Chapter 13 on statistical network models. The first tutorial covered the case of cross-sectional network data. Here, we assume that a researcher has data on at least two time points and is interested in modeling change in the network over time. In this tutorial, we will walk through the estimation and interpretation of separable temporal exponential random graph models (STERGM). “
About Us © 2026 Section on Complexity and Network Studies. All rights reserved.