Simulation from Knecht Friendship Data – Four wave study on adolescent's behavior and relations using an actor-driven statistical model in SIENA
The dataset consists of repeated surveys of friendship nominations among adolecents. The data was gathered by Andrea Knecht, PhD student, building on methods developed by Chris Baerveldt, initiator and supervisor of the project. The project is funded by the Netherlands Organisation for Scientific Research NWO, grant # 401-01-554.
The SIENA software is a package for estimating statistical models of network dynamics and simulating plausible sequences of changes in a network over time. During a brief SIENA/SoNIA work session at ICS program in Groningen, we explored various posibilities for viewing simulated transition networks generated by SIENA using parameters estimated from the data. The movie here shows the results of one of these simulations. The first and last frames correspond to the observed networks at two waves of the survey, the intermediate frames of the movie show a probable sequence of changes generated by the estimated model of dynamics. The technique is very experimental and currently requires a specially modified versions of SIENA, but the possibility of coupling the programs is exciting.
See for references:
- Knecht, A., Baerveldt, C., & Steglich, C. (2005). Friendship and delinquency in early adolescence. A study of selection and influence processes. Paper presented at the Sunbelt XXV conference on social network research, Los Angeles, USA, February 18, 2005. (currently under review)
- Powerpoint slides of an earlier version and first results are at http://www.ppsw.rug.nl/~steglich/dynamics/Piran2004/presentations/KnechtBaerveldt.ppt
- Boer, P., Huisman, M., Snijders, T.A.B., and Zeggelink, E.P.H. 2003. StOCNET: an open software system for the advanced statistical analysis of social networks. Version 1.4. Groningen: ProGAMMA / ICS. http://stat.gamma.rug.nl/stocnet/
- Snijders, Tom A.B. 2001. “The Statistical Evaluation of Social Network Dynamics.” Sociological Methodology:361-395.