Tracy Sweet, University of Maryland

Latent variable models for social network data

Invited Speaker

To accommodate the ill-defined dependence structure among network ties, one class of network models uses latent variables. Conditionally independent tie or dyad (CID) models are also relatively simple to fit, allowing for a number of interesting extensions. In this talk, I will present two examples from my own research: a multilevel model mediation model and a latent variable model for social influence as well as discuss some future directions.

about the speaker

Tracy Sweet is an Associate Professor in the Measurement, Statistics and Evaluation program in the Department of Human Development and Quantitative Methodology.  She completed her Ph.D. in Statistics at Carnegie Mellon University and a M.A. in Mathematics at Morgan State University. Her research focuses on methods for social network analysis with particular focus on multilevel social network models. Recent projects include network interference, measurement error, and missing data. She serves as the Associate Director of Research for UMCP for the Maryland Longitudinal Data System Center and is currently overseeing projects applying data science and statistical methods to large-scale educational data. Finally, Dr. Sweet is committed to improving diversity in the fields of statistics and quantitative methodology.

Log in