February 14, 2019
All Day
209 W Eighteenth Ave (EA), Room 170
Title
Bayesian Modeling Strategies for Multivariate nonGaussian Time Series Data
Speaker
Refik Soyer, Department of Management Science, George Washington University
Abstract
Multivariate non Gaussian time series of correlated observations are considered. In so doing, we focus on multivariate time series of counts and durations. Dependence among series arises as a result of sharing a common dynamic environment. We discuss characteristics of the resulting multivariate time series models and introduce dynamic versions of some known multivariate distributions. We develop Bayesian inference for the models using Markov chain Monte Carlo and particle filtering methods and discuss computational issues. The proposed models are illustrated using actual bivariate time series data.
Note: Seminars are free and open to the public. Reception to follow.