In Module 2, we will draw a Bayesian model as a graph and distinguish posterior distribution, posterior predictive distribution, and expected loss or cost. We will also calculate distributions without closed form, recognizing that we can use computational methods to draw from the distribution even when there's no straight-forward equation to define them. Be sure to review the learning objectives before beginning work in this module.

In Module 3, we will employ R and the Stan platform for statistical modeling. You will explore Bayesian methods in data analysis and modeling; work with posterior distributions, distributions without closed form, directed acyclic graphs, and Markov Chain Monte Carlo algorithms. You will also be introduced to Bayesian hierarchical models, which estimate subgroup parameters relative to the parameters of a larger parent group. Be sure to view the course introduction video and review the learning objectives before beginning work in this module.