Most courses on social network analysis (SNA) focus on descriptive SNA, such as measuring the density of a network, identifying subgroups within a network, or examining the centrality of actors within a network. Inferential SNA, which focuses on explaining the formation of networks and behaviors and beliefs of actors embedded in networks, by contrast, is often eschewed.
This short course is an introduction to inferential SNA. The course consists of two modules – (1) network formation models and (2) network effect models.
(1) Network formation modeling
This module focuses on modeling network formation using exponential random graph models (ERGMs). ERGMs are a principled way of modeling friendship formation in which the whole network of interdependent dyads is considered one observation from a complex multivariate distribution. In this module, I first discuss why standard regression models will fail to properly model network data, then introduce ERGMs, and finally discuss how ERGMs can be used in combination with simulation techniques to understand how micro-level mechanisms shape the macro-level structure of networks. The module consists of a lecture and a hands-on R tutorial.
(2) Network effect modeling
This module focuses on models to explain how the behaviors and beliefs of actors are influenced by the networks in which they are embedded. Covered are cross-sectional, panel, and dynamic panel models to estimate exogenous and endogenous peer effects. The module consists of a lecture and a hands-on R tutorial.
Feel free to use any of these materials but please cite me using this reference:
Rosche, Benjamin (2023). Introduction to Inferential Social Network Analysis. https://benrosche.com/teaching/isna-workshop/