Having Bayes’ Theorem in the Scientific Toolkit: Experiences and Reflections

Uncertainty is everywhere, whether we’re talking about the weather, a clinical diagnosis, or which cafe to go to. Bayesian statistics provides a rigorous framework for dealing with all forms of uncertainty that boils down to one very simple equation: Bayes’ theorem. Come hear a leading expert on the topic talk about his thoughts on what an 18th century formula has to teach us today.

Paul Gustafson will begin in a discussion of the basics of Bayes’ theorem, and then describe, non-technically, what the workflow looks and feels like for the Bayesian analysis of a dataset. Then, he will describe some scientific applications where he thinks Bayesian inference is particularly helpful. This will segue to his views on some very nice features of “being Bayesian,” as well as an offering of some contrarian perspectives. Time allowing, he will also discuss the extent to which everyday human reasoning is, or isn’t, Bayesian in nature.

Paul Gustafson is a Professor in the Department of Statistics at the University of British Columbia, Vancouver. He is a Fellow of the American Statistical Association, the 2008 recipient of the CRM-SSC Prize in Statistics, and the 2020 Gold Medallist of the Statistical Society of Canada. His research interests include Bayesian methods, causal inference, evidence synthesis, measurement error, and partial identification. He has authored two books: Measurement Error and Misclassification in Statistics and Epidemiology: Impact and Bayesian Adjustments (2004), and Bayesian Inference for Partially Identified Models: Exploring the Limits of Limited Data (2015). He was the Editor in Chief of the Canadian Journal of Statistics (2007-2009), and is currently the Special Editor for Statistical Methods for the journal Epidemiology. At UBC, Paul served as a founding co-director of the Master of Data Science program, and he has just embarked upon a second term as Head of the Department of Statistics.