Seminar - Paul Gustafson

Event Date: 

Wednesday, June 2, 2021 - 3:30pm to 4:30pm

Event Location: 

  • Zoom Meeting

Title: Tales of Bayesian Inference from the Pandemic: Partial Progress via Partial Identification


Partially identified models generally yield “in between” behavior. As the sample size goes to infinity, the posterior distribution on the target parameter heads to a distribution narrower than the prior distribution but wider than a point-mass. Such models arise naturally in many areas, including public health and epidemiology. As exemplars, we describe two models recently applied to pandemic data. One involves inferring an epidemic curve in light of an imperfect diagnostic test with imperfect knowledge of its imperfections. The other involves meta-analytic inference about infection fatality rates, via a combination of surveillance data and sero-survey data. We use these as examples to comment on general issues with Bayesian inference in partially identified models. We focus on information flow, investigating how much can we realistically expect to learn without the benefit of full identification.

Paul Gustafson is a professor and head of the Department of Statistics at University of British Columbia. Gustafson's research centres around the Bayesian approach to statistical inference. He has published more than 140 articles in peer-reviewed journals, conference proceedings and book chapters, and has authored two books. He has successfully supervised 35 graduate students and three post-doctoral fellows. A fellow of the American Statistical Association, Gustafson received the CRM-SSC Prize in Statistics in 2008, a national award jointly sponsored by the Statistical Society of Canada and the Centre de recherches mathématiques. He serves as the statistics editor for Epidemiology (since 2014) and has been an associate editor for a number of other journals. He also served as Editor in Chief for the Canadian Journal of Statistics (2007-2009).


Prof. Paul Gustafson