Stochastic Models
A brief introduction to stochastic modeling of network data, focusing on exponential random graphs models (ERGM).
Readings
Exercises
Practice 15.1 (requires R, see below)
Slides
Video
26 Apr part 1
(let me know if any problems -- Yuja seems to have two copies, and one starts in the middle of class)
Supplementary Readings
Robins, G., P. Pattison, Y. Kalish, and D. Lusher (2007). On exponential random graph models for cross-sectional analysis of complete networks: An introduction to exponential random graph (p*) models for social networks. Social Networks, 29(2): 173-191 [pdf]
Snijders, T.A.B., G. van de Bunt, G., and Ch. Steglich (2010). Introduction to stochastic actor-based models for network dynamics. Social Networks, 32: 44-60 [pdf]
Butts, C. T., & Marcum, C. S. (2017). A relational event approach to modeling behavioral dynamics. In Group processes (pp. 51-92). Springer, Cham.
ERGM Software
Class will mostly be lecture, but I will briefly demonstrate ERGM modeling using R. If you want to follow along, you will need to install R and, for convenience, R-Studio (in that order). Then install the sna and ergm packages:
install.packages("sna")
install.packages("ergm")
library(sna)
library(ergm)
Then, in order to have the datasets we will use, you will need to install the xUCINET package. This is not available yet through the install.packages command, so you have to download this zip file: xUCINET_0.0.0.9014.zip and then follow these instructions.
Finally, you can download the R-script we will be using in class here.