The Statistics Seminar speaker for Wednesday, November 8, 2017, is James Hobert, professor in the Department of Statistics at the University of Florida. He received his PhD in Statistics from Cornell University in 1994. Hobert's main research area is Markov chain Monte Carlo. He has published over fifty research articles, many in top-tier statistics journals, and has served as Associate Editor for Journal of the Royal Statistical Society (Series B), Annals of Statistics, and Electronic Journal of Statistics. Hobert was elected Fellow of the Institute of Mathematical Statistics in 2006.
Talk: Convergence analysis of MCMC algorithms for Bayesian robust multivariate regression
Abstract: Let $\pi$ denote the intractable posterior density that results when the likelihood from a multivariate linear regression model with errors from a scale mixture of normals is combined with the standard non-informative prior. There is a simple data augmentation (DA) algorithm and a corresponding Haar PX-DA algorithm that can be used to explore $\pi$. I will explain how the behavior of the mixing density near the origin is related to the rate at which the corresponding Markov chains converge. (This is joint work with Yeun-Ji Jung, Kshitij Khare and Qian Qin.)