You are here: Home News
NEWS
Summer School in Analysis of Longitudinal Network Data using SIENA
15-19 June 2009
Summer School in Analysis of Longitudinal Network Data using SIENA
(June 15-19, Bertinoro, Italy)
taught by Prof. Christian Steglich organized by Dipartimento di Scienze Aziendali University of Bologna & Forlì
School objectives
The course’s primary topic is the approach of stochastic, actor-based modelling to the analysis of longitudinal data on complete networks using the analytical tools implemented in the SIENA software (Snijders, Steglich, Schweinberger & Huisman, 2007). The main focus is on the analysis of network evolution processes and processes of co-evolution between social networks and changeable actor attributes. As examples for simple network evolution, one can think of friendship formation among adolescents, the dynamics of trust between employees of a firm, or contracting between firms. Examples for co-evolution with actor attributes would be the joint dynamics of substance use and friendship in adolescence, of employee performance and the web of informal relations at the workplace, or of a firm’s financial success and the web of patent citations between firms. For studying such processes, longitudinal, complete network data are necessary. In this workshop, we assume that the same network is measured on the same group of actors at several discrete moments in time. Participants will learn to analyse such data by estimating stochastic, actor-based models, as described by Snijders, van de Bunt & Steglich (2009), which are implemented in the SIENA program. This modelling approach allows for inclusion of various endogenous network effects (reciprocity, transitivity, cycles, popularity, etc.), effects of actor attributes (i.e., connected to the sender, the receiver, or the similarity between sender and receiver), and of dyad-level covariates (i.e., other networks).
The workshop will focus on the intuitive understanding of the model and operation of the software, making use of several examples on data sets provided with the software. After a general introduction, model extensions to various types of network data will be addressed.
Instructor
Christian Steglich is a leading authority on the statistical analysis of longitudinal networks. He studied Mathematics and Computer Sciences at the TU Berlin, followed by a doctoral study at the Interuniversity Center for Social Science Theory and Methodology (ICS) in Groningen (The Netherlands). Since his PhD he has been part of the team developing the SIENA software for longitudinal social network analysis and exponential random graph modelling, and has been teaching workshops on the use of SIENA throughout the world since 2004. Currently, he is employed as associate researcher at the Faculty of Behavioural and Social Sciences at the University of Groningen. His latest research is embedded in the European Collaborative Research Project “Dynamics of Networks and Actors across Levels”, funded under the ESF EUROCORES scheme, and the project “Social Network Analysis of Peers and Smoking in Adolescence”, funded by the Medical Research Council of the United Kingdom.
Prerequisites
Participants should have a basic understanding of statistical principles and social networks. Ideally, they should be involved in a research project in which they can put the software to use. For this, we expect every participant to send a short summary of their research background (max. 1 page A4) detailing the purpose why they want to attend the course, and (if applicable) give a short sketch of the data sets and research hypotheses to be addressed in their own research. Participants are expected to bring their own Windows-operated laptop to the workshop, ideally with a pre-installed version of the StOCNET software package (instructions will be sent after successful registration). Participants who want to analyse their own data should ensure that the data sets are in a format that the software can read, before the course begins. For this to happen smoothly, please contact c.e.g.steglich@rug.nl at least one week prior to the course.
The Venue & Format
The 5 day course will be hosted by the The University Centre of Bertinoro, a stunning medioeval fortress located on the hills of Forli, about 60 Km away from Bologna. Bertinoro is easily reached by train and taxi from Bologna and is close to many splendid Italian locations such as Ravenna, Rimini on the Adriatic coast, and the Republic of San Marino (all within 35km) as well as some less well-known locations like the thermal springs of Fratta Terme, the Pieve di San Donato in Polenta and the castle and monastic gardens of Monte Maggio (http://www.ceub.it/inglese/centro_universitario.htm)
The workshop starts Monday, June 15th, at 14:00 and ends on Friday, June 19th, around lunchtime. In-between, course days will consist of a morning session (9:30-13:00) and an afternoon session (14:00-17:00), each session will consist of a plenary introduction to the session’s topic, a demonstration of how to address this topic with the software, and a practical exercise for the participants to work on. The precise schedule will be made public in due course.
Course Material
Robins, Garry L., Tom A.B. Snijders, Peng Wang, Mark Handcock, and Philippa Pattison. Recent developments in exponential random graph (p*) models for social networks. Social Networks 29 (2007), 192-215.
Snijders, T.A.B., van de Bunt, G.G., and Steglich, C.E.G. (2009). Introduction to actor-based models for network dynamics. Social Networks, in press.
Snijders, Tom A.B., Steglich, Christian E.G., Michael Schweinberger and Mark Huisman. Manual for SIENA version 3.1. University of Groningen: ICS / Department of Sociology; University of Oxford: Department of Statistics, (2007).
The manuals for the StOCNET program package and the SIENA module are available from the respective websites http://stat.gamma.rug.nl/stocnet/ and http://stat.gamma.rug.nl/siena.html. The SIENA website also contains a list of (and in many cases: links to) articles on SIENA and applications using SIENA, including both Snijders et al. references given above. These articles are not required to be read in advance to the course, but are a helpful addition. Several examples treated
during the course will be taken from these articles. The slides that will be used during the workshop, as well as the assignments and data sets will be made available prior to the course.
Registration fees and application
Participation is open to doctoral and post-doctoral students as well as faculty. Deadline for applications is June, 1 2009.
PhDs & Post-Docs: Euro 400
Faculty: Euro 600
These fees are subsidized by FRIDA and are charged exclusively to recoup all remaining direct expenses. The fee entitles participants to lecture notes, lunches, refreshments and coffee breaks throughout the week. Participants are expected to make their own arrangements for housing. Admitted participants will receive details on the payment procedure and accommodation options (inexpensive lodging is available within the fortress). Registration will be confirmed as soon as the payment is received. Applications should be sent exclusively to this address: summerschool.sa@unibo.it
More Info:
