2E Advanced Social Network Analysis I - Selection Mechanisms and Social Structure
John Skvoretz, University of South Florida (week 1)
Filip Agneessens, University of Groningen (week 2)
22 July - 2 August (two week course / 35 hrs)
This course covers advanced statistical methods for analyzing social network data, focusing on testing hypotheses about network structure (e.g. reciprocity, transitivity, and closure), and the formation of ties based on attributes (e.g. homophily). We begin with statistical models for the local structure of dyads and triads, then move onto statistical models based on the assumption of dyadic independence, and then cover recent advances in statistical models that permit structured forms of dependence between dyads. Topics include random graph distributions, statistical models for local structure (dyads and triads), biased net models for complete networks and for aggregated tie count data, dyadic independence models (p2 models), exponential random graph models (p* models), and the comparison of network structures between groups. We also pay attention to possible problems related to missing data. Software used includes: Carter Butts “sna” package in R, PNET, XPNET, BPNET and “ERGM” in R. Additional custom based programs for R will be made available throughout the course.
The course aims to familiarize participants with the formal statistical analysis of network data for selection mechanisms. Participants will become familiar with specific programmes designed for these analyses and with the mathematical basis for the modelling approaches, and they will learn how to conduct statistical analyses of their own network data. Participants are encouraged to bring with them their own network data to be analyzed using the techniques covered.
In general the course focuses on how do the characteristics of a network of interest differ from chance? At the end of the course, participants should be able to answer questions, such as:
- Is there more reciprocity in an advice network than could be expected by chance? And is the effect larger in one network than another?
- Is there a tendency towards homophily? (do smokers tend to be friends with other smokers? and do non-smokers tend to be friends with other non-smokers)?
- Is there more transitivity (are friends of friends also friends) or closure or cyclicality in a network than expected by chance, controlling for the degree distribution?
- Do advice and friendship ties tend to overlap (multiplexity)?
- Are actors loyal with respect to the events they attend, and do specific characteristics explain their choice of events (e.g. do Republican Senators tend to cosponsor bills if other Republican Senators also cosponsor that bill)?
- Considering the friendship network for different classes at the same time, is there an overall tendency towards clustering? Are there differences in tendency between classes?
The course aims to familiarize participants with the formal statistical analysis of network data. Participants will become familiar with specific programmes designed for these analyses and with the mathematical basis for the modelling approaches, and they will learn how to conduct statistical analyses of their own network data. Participants are encouraged to bring with them their own network data to be analyzed using the techniques covered.
Participants should have taken an introductory course in social network analysis, so be familiar with such terms as mutuality, degree, centrality, n-cliques, structural equivalence, geodesic, row-stochastic. Participants should also have taken a basic course in (logistic) regression analysis.
Scott, J. 1992. Social Network Analysis. Sage
Representative Background Reading
Wasserman, S., and Faust, K. 1996. Models and Methods in Social Network Analysis. Cambridge University Press.
Carrington, P.J., J. Scott, and S. Wasserman. 2005. Models and Methods in Social Network Analysis. Cambridge University Press.