The study program “The Bayesian Approach to Data Analysis” provides a powerful framework for handling uncertainty in observations, model parameters, and model structure using probability theory. It is therefore not surprising that Bayesian methods are increasingly being used in statistical and computational inference across both science and industry.

Probabilistic programming languages make it easier to specify and fit Bayesian models. However, they still leave us with many options for constructing, evaluating, and applying these models — as well as numerous remaining computational challenges.

Video produced by Christoph Bertolo from FlexX Film Produktion.