General Departmental Seminar Series
Mixed Effects Models for Dyadic Network Data
Peter Hoff, PhD, Departments of Statistics and Biostatistics and
Center for Statistics and the Social Sciences, University of Washington
Friday, February 13, 2004, 12-1:15 p.m.
3070 Grainger Hall, 975 University Ave.
Dyadic data consist of measurements that are made on pairs of objects or under a pair of conditions. Such data arise in the study of social networks, international trade or relations, ``round robin'' experiments in psychology, disease transmission, and many other areas.
One impediment to the statistical analysis of such network data has been the difficulty in modeling the dependence among the observations. In the very simple case of binary (0-1) network data, some researchers have parameterized network dependence in terms of exponential family representations. Accurate parameter estimation for such models is difficult, and the most commonly used models often display a significant lack of fit. Additionally, such models are generally limited to binary data. In contrast, mixed effects models have been a widely successful tool in capturing statistical dependence for a variety of data types, and allow for prediction, imputation, and hypothesis testing within a general regression context. We propose novel random effects structures to capture network dependence, which can also provide graphical representations of network structure and variability.
This talk is jointly sponsored by the Social Sciences and Statistics Seminar and the Department of Biostatistics and Medical Informatics.
Return to seminar list