To anybody interested.

Within the ICS (Interuniversity Center for Social Science Theory
and Methodology), there is a vacancy for a Ph.D. student on
statistical methods for the dynamics of social networks.
This is a paid position for 4 years for the preparation of a
Ph.D. thesis at the University of Groningen (The Netherlands).
The vacancy procedure is already under way, but it appears
difficult to find suitable candidates.
The description of the research project is given below.
Candidates should have a good background in statistics
Any person interested is requested to reply as soon as possible to
Tom Snijders, <[log in to unmask]>
Replies should be sent preferably before June 5, 1999,
but replies sent later during June can also be considered.

More information about the ICS can be found
at the website of the ICS <http://www.ppsw.rug.nl/ics/index.htm>.

The project description is as follows.

Statistical methods for the joint development of individual behavior
and peer networks

Aim
The elaboration of statistical models for the joint evolution of
individual behavior and the network of relations in a closed group,
and the application of this model - in collaboration with other
researchers - to the development of childrens' behavior in the early
years of primary school.

Social science background
In childrens' development, there are continuous mutual influences
between the development of individual behavior, of dyadic
friendships, and of social interactions in the peer group. A large
part of this interaction takes place at school. Problems in dealing
with peers and in the adjustment to the daily school routine can be
an important source of concern and can be related to later behavioral
problems. Research into this development process requires statistical
analysis methods for longitudinal data on social networks, in which
the changing pattern of relations and the changing behavior of the
individuals are regarded simultaneously as outcome variables. At this
moment, there exist no satisfactory methods for the statistical
analysis of such data. In this project, recently developed methods
for the analysis of longitudinal data on relational networks will be
extended with a model for changes in the behavior of the persons in
the network, including network effects on such behavior changes. The
new model will have to take account of theoretical notions of
interpersonal behavior and its development.

Statistical background
The statistical models will be based on computer simulation models
for the simultaneous development of relational networks and
individual behavior. These simulation models have to be as much as
possible explicit expressions of theoretical models for this
development. Data analysis for such simulation models can be based on
Markov Chain Monte Carlo methods using the Robbins Monro algorithm,
as proposed in Snijders (1996) and Snijders and Van Duijn (1997). A
method for the development of relational networks only, program
SIENA, is already available. This method will be extended in the
proposed project.

Research design
This is primarily a statistical project, which includes a close
collaboration with social scientists. The Ph.D. student needs to have
a good training in statistics and interest in social science
applications. The project is part of the research program Social
Development: Longitudinal and Dynamical Aspects of Dyadic and Group
Processes, in which researchers from the universities of Utrecht
and Groningen collaborate. Data are collected as part of an ongoing
longitudinal study in more than 50 primary schools.

Literature
Snijders, T.A.B. (1996), Stochastic actor-oriented dynamic network
analysis.
Journal of Mathematical Sociology 21, 149-172.
Snijders, T.A.B. & Van Duijn, M.A.J., (1997), Simulation for
statistical inference in dynamic network models.
In: Conte, R., Hegselmann, R. Terna, P. (eds.), Simulating social
phenomena, 493-512. Berlin: Springer.

This and more information can also be found at the web site,
<http://stat.gamma.rug.nl/snijders/>

*******************************************************************
Tom A.B. Snijders
ICS
Dept. of Statistics, Measurement Theory, and Information Technology
University of Groningen
Grote Kruisstraat 2/1
9712 TS Groningen
The Netherlands

Fax +31 - (0)50 - 3636304
Tel. +31 - (0)50 - 3636188 (office)
     +31 - (0)50 - 3636184 (secretary)
     +31 - (0)50 - 3129152 (home)

E-mail [log in to unmask]
Home page http://stat.gamma.rug.nl/snijders/
*******************************************************************


%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%