We're going Bayesian this month as we welcome Jonah Gabry back to talk about the role of visualization in Bayesian analysis.
About the Talk:
Bayesian data analysis is about more than just computing a posterior distribution, & Bayesian visualization is about more than trace plots of Markov chains. Practical Bayesian data analysis, like all data analysis, is an iterative process of model building, inference, model checking & evaluation, & model expansion. We will discuss how visualization is helpful in each of these stages of the Bayesian workflow (and statistical workflow more broadly) & is indispensable when drawing inferences from the types of modern, high-dimensional models that are used by applied researchers.
About Jonah:
Jonah Gabry is a core developer of the widely used open-source Stan software for statistical modeling & a researcher in statistics at Columbia University collaborating primarily with Andrew Gelman on methods & software for Bayesian data analysis. Jonah is an author of the rstan & rstanarm R packages, which provide interfaces to Stan, as well as the author of the shinystan & bayesplot packages for model visualization, & the loo package for model comparison. In addition to developing statistical software, Jonah is affiliated with several research centers at Columbia, including the Applied Statistics Center, the Institute of Social & Economic Research & Policy, & the Population Research Center. Outside of academia, he has provided statistical consulting to professional sports teams, major publishing companies, & other businesses, as well as US & European Union government agencies.
Pizza (nyhackr.org/pizzapoll.html) begins at 6:30, the talk starts at 7, then after we head to the local bar.