Skip redundant pieces
 
Quant Home KU Quant Program Summer Institute Academic Resources Quant News Quant Services
 
Social Network Dynamics
 

Five-day Course • June 15 –19, 2009• Lawrence, Kansas

Sponsored by the Quantitative Psychology Training Program of the Department of Psychology at the
University of Kansas

Institute Overview

This is a one-week course designed primarily for researchers who are currently doing longitudinal social network research or who are embarking upon it. More specifically, the course is about how to analyze panel data on complete social networks; "complete" meaning that the collection of all network ties within one or several groups is being studied, "panel"; that it is observed at two or more discrete moments in time. The course will treat statistical modelling of network dynamics according to the stochastic actor-based approach (Snijders 2001, 2005; Snijders, Steglich and Schweinberger, 2007). The course will use the computer program SIENA and will consist of a mixture of classroom teaching and hands-on computer work. Some attention will be paid also to non-longitudinal network models, the so-called Exponential Random Graph Models. 

Instructors

Tom A.B. Snijders , Ph.D., Professor of Statistics in the Social Sciences at the University of Oxford,
and Professor of Methodology and Statistics in the Faculty of Behavioral and Social Sciences at the
University of Groningen .

Software and Computer Support

Participants are expected to bring their own laptops, on which SIENA can be installed before or during the course. It is expected that participants have a basic knowledge of statistical modeling. No specific prior knowledge of network analysis, or of the SIENA program, is assumed. However, attendees who know nothing about social network analysis are adviced to read some introductory material as mentioned below in the reference list. Further information and publications about this method and software can be found at http://www.stats.ox.ac.uk/siena/

Syllabus

(Provisional)
Monday.  Introduction to dynamic network modeling
9:00-10:30 An introduction to stochastic actor-oriented models for network dynamics
10:30-10:45 Break
10:45-12:00 Introduction to SIENA
12:00-1:00 Lunch (provided)
1:00-2:30 Examples of applications.
2:30-2:45 Break
2:45-4:00 Computer work with Siena
4:00-4:15 Break
4:15-5:00 Continuation computer work
6:00 Barbeque at Little/Hawley home (provided) 
Tuesday. 
Continued dynamic network modeling; Modeling of networks and behavior
9:00-10:30 The basic estimation algorithm. Parameter interpretation.
10:30-10:45 Break
10:45-12:00 Model specification; Special topics: composition change, structurally determined values, missing values.
12:00-1:30 Lunch (on own)
1:30-3:00 Introduction to co-evolution of networks and behavior.
3:00-3:15 Break
3:15-5:00 Computer work with Siena: co-evolution of networks and behavior. 
Wednesday.  Examples and further background.
9:00-10:30 Diverse examples
10:30-10:45 Break
10:45-12:00 Continuation of computer work with SIENA
12:00-1:00 Lunch (provided)
1:00-2:30 Model specification. Goodness of fit tests.
2:30-2:45 Break
2:45-4:00 Simulation with Siena
4:00-4:15 Break
4:15-5:00 Continuation computer work  
Thursday.  Exponential random graph models; Multilevel dynamic network analysis
9:00-10:30 Non-longitudinal network models: Exponential Random Graph Models (ERGMs).
10:30-10:45 Break
10:45-12:00 Continuation of ERGMs, computer work with pnet or statnet.
12:00-1:30 Lunch (on own)
1:30-3:00 Meta-analysis of dynamic network analysis results.
3:00-3:15 Break
3:15-5:00 Computer work with Siena: running Siena through batch files. 
Friday.  Communication of results; New developments.
09:00-10:30 Communication of results to a wider audience.
10:30-10:45 Break
10:45-12:00 Last question time.
12:00-1:00 Lunch (provided)
1:00-5:00 Individual consultation on data analysis projects 

Literature

Those who are new to the field of network analysis are advised to have a look at one (or both) of the two general introductory texts on social network analysis mentioned below, to get a general impression of this encompassing domain. Those who like to do some introductory reading more specifically on the topic of this course are advised to read Snijders, Steglich, and van de Bunt (2008) as a non-technical introduction to modeling network dynamics. Further references and the software can be found at http://www.stats.ox.ac.uk/siena/

This literature list is not final, and will be updated for the course.

Introductory literature, social network analysis

The free online introductory textbook on social network analysis (2005), Introduction to social network methods, by Robert Hanneman and Mark Riddle. http://faculty.ucr.edu/~hanneman/nettext/

John Scott, Social Network Analysis: A Handbook. 2nd edition. Sage, 2000.

Stochastic actor-based models for network dynamics

Snijders, Tom A.B., The statistical evaluation of social network dynamics. M.E. Sobel and M.P. Becker (eds.), Sociological Methodology-2001, 361-395. Boston and London: Basil Blackwell.
(This is a general technical exposition of the method for modeling network dynamics.)

Snijders, Tom A.B. Models for Longitudinal Network Data. Chapter 11 in P. Carrington, J. Scott, & S. Wasserman (Eds.), Models and Methods in Social Network Analysis. New York: Cambridge University Press (2005), p. 215-247.
(This is another general, rather technical exposition of the method for modeling network dynamics, presumably written in a somewhat more accessible style than the preceding article.)

Snijders, T. A. B., Steglich, C., & Schweinberger, M. Modeling the co-evolution of networks and behavior. In K. van Montfort, H. Oud & A. Satorra (Eds.), Longitudinal models in the behavioral and related sciences, p. 41-71. Mahwah, NJ: Lawrence Erlbaum (2007).
(This is a general technical exposition of the method for modeling the interdependent dynamics of networks and behavior.)

Snijders, Tom A.B., Christian E.G. Steglich, Michael Schweinberger, and Mark Huisman. (2007). Manual for SIENA version 3. Groningen: University of Groningen, ICS. Oxford: University of Oxford, Department of Statistics. http://www.stats.ox.ac.uk/~snijders/siena/sie_man31.pdf

Snijders, T.A.B., Steglich, C.E.G., and van de Bunt, G.G. (2008). Introduction to actor-based models for network dynamics. Submitted for publication. http://www.stats.ox.ac.uk/~snijders/siena/SnijdersSteglichVdBunt2008.pdf
(This is a general non-technical introduction to the methods for modeling network dynamics as well as for modeling the interdependent dynamics of networks and behavior.)

Steglich, Christian E.G., Snijders, Tom A.B. and Pearson, Michael. (2007). Dynamic Networks and Behavior: Separating Selection from Influence. Submitted for publication. http://www.stats.ox.ac.uk/~snijders/siena/SteglichSnijdersPearson2007.pdf
(This is a general exposition of the method for modeling the interdependent dynamics of networks and behavior, with many connections to other social science research on this topic.)

Contact Information

For information on course content, contact Noel A. Card ncard@email.arizona.edu or Todd D. Little yhat@ku.edu.

 


Please send questions or comments concerning this Web site to Donald Gay.