Network Modeling (Winter 2012/2013)

Social network analysis, i.e., the joint analysis of actors and relations among them, rapidly gains importance in many scientific and commercial applications. Examples range from studies of organizational and communication networks over to the analysis of Webbased user interaction. Statistical approaches in social network analysis are applied to model, estimate, and predict social interaction and behavior based on empirical data. In this course you will learn mathematical and methodological foundations for modeling social networks. In the first part we treat models for timeindependent networks and in the second part we model the evolution of networks over time. This course is part of a set of three related lectures offered by the Algorithmics group: Network Analysis, Network Dynamics, and Network Modeling. Note that these courses can be taken independently of each other and in any order. Prerequisites Knowledge of basic mathematical concepts, as well as mathematical soft skills, i.e., the ability to understand and work with mathematical definitions, theorems, and proofs. 
Schedule
Lecture (Viviana Amati & Jürgen Lerner)  Wed 13:3015:00 h (s.t.) room: E 403 (weekly) 
Tutorial (Mehwish Nasim & Bobo Nick)  Wed 17:0018:30 h (s.t.) room: R 511 (fortnightly) 
Exams (oral)  February 13 (individual times); room: E 201 
Exercises
Most documents are only locally accessible  see possibilities for remote access.New assignments will be placed online in the evening after the lecture.
Solutions are due on Tuesdays, 10am (if there is a tutorial the next day), or Wednesdays 13:30h (otherwise).
Place solutions on the box in front of E203, or send an email with attached pdf  if permitted by the deadline, solutions can be handed over at the beginning of the lecture, too.
no.  online  due  tutorial  download 

0  24.10.12  30.10.12  31.10.12  
1a  31.10.12  07.11.12  14.11.12  
1b  07.11.12  13.11.12  14.11.12  
2a  14.11.12  21.11.12  28.11.12  
2b  21.11.12  27.11.12  28.11.12  
3a  28.11.12  05.12.12  12.12.12  
3b  05.12.12  11.12.12  12.12.12  
4a  12.12.12  19.12.12  09.01.13  
4b  19.12.12  08.01.13  09.01.13  
5a  09.01.13  16.01.13  23.01.13  
5b  16.01.13  22.01.13  23.01.13  
6a  23.01.13  30.01.13  06.02.13  
6b  30.01.13  05.02.13  06.02.13 
Material
Most documents are only locally accessible  see possibilities for remote access.Data
 Data can be downloaded here
Slides
 Stochastic actororiented models (slides) last updated: February 07, 2013.
 Stochastic actororiented models (slides) as handout (4 slides per page) last updated: February 07, 2013
 Static Network Models (slides) last updated: December 4, 2012.
 Static Network Models handout (slides) last updated: December 17, 2012 (fewer uncovering steps).
Lecture notes
 Stochastic actororiented models (lecture notes) last updated: February 06, 2013 (will be extended and updated during the lecture).
 Static Network Models (lecture notes) last updated: October 17, 2012 (will be extended and updated during the lecture).
Code example
 R code illustrating degeneracy of some ergms used in the lecture on December 5, 2012.
 R code illustrating sampling from an ergm used in the lectures on November 21 & 28, 2012.
 R code illustrating the parameter estimation of the SAOM used in the lectures on December 19, 2012 & January 23, 2013.
 R code illustrating the simulation of the network evolution in the SAOM used in the lecture on January 09, 2013.
 R code illustrating the parameter estimation of the coevolution of network and behavior in the SAOM used in the lecture on January 30, 2013.
 Link to the R project page.
Literature
(list will be extended)Lecture topics
 Robins, Pattison, Kalish, and Lusher: An introduction to exponential random graph (p*) models for social networks. Social Networks 29(2):173191, 2007. (local copy)
 Snijders, van de Bunt, and Steglich: Introduction to stochastic actorbased models for network dynamics. Social Networks 32(1):4460, 2010. (local copy)
 Snijders, Koskinen, and Schweinberger: Maximum Likelihood Estimation for Social Network Dynamics. Annals of Applied Statistics 4(2):567588, 2010. (local copy)
 Steglich, Snijders, and Pearson: Dynamic Networks and Behavior: Separating Selection from Influence. Sociological Methodology 40(1):329393, 2010. (local copy)
 Batagelj, Brandes: Efficient Generation of Large Random Networks. Physical Review E 71, 036113, 2005.
Background and further reading
 Lazer, Pentland, Adamic, Aral, Barabási, Brewer, Christakis, Contractor, Fowler, Gutmann, Jebara, King, Macy, Roy, Van Alstyne: Computational Social Science. Science 323(5915), 721723, 2009.
 Brandes, Erlebach (Eds.): Network Analysis. LNCS 3418, Springer, 2005.
 Wasserman, Faust: Social Network Analysis. Cambridge Univ. Press, 1994.