We discuss the kinds of hypotheses that we typically formulate in social network analysis, and talk about regression-based methods for testing them. The principal issue in using standard statistical techniques in the network context is the lack of independence among cases. We discuss the use of randomization (aka permutation) tests to deal with this autocorrelation.
Tutorials and Handouts
QAP Regression
Supplementary Readings (optional)
Dekker, D., Krackhardt, D., & Snijders, T. A. (2007). Sensitivity of MRQAP tests to collinearity and autocorrelation conditions. Psychometrika, 72(4), 563-581. [pdf]
Krackhardt, D. 1988. "Predicting with networks: Nonparametric multiple regression analysis of dyadic data."Social Networks. 10:359-381. [pdf]
Additional Resources