This course enables students to propose and fit a fully Bayesian statistical model to a wide variety of data sets when data is sparse and expert judgments need to be incorporated. It covers generalized linear multilevel models with extensional discussions of measurement error, missing data, and Gaussian process models for spatial and network autocorrelation. By using complete R code examples throughout, this module provides a practical foundation for performing statistical inference. It thus prepares students for more advanced or specialized statistical modeling.
A Describe differences between Bayesian and classical approaches to statistical inference; B Develop an appropriate Bayesian solution, describe the model for data and parameters precisely in mathematical notation, fit the model to data, and then relate the data analysis back to the original problem when given a non-standard problem description; C Describe differences between different computational methods for deriving posterior distributions for parameters, understand how they work, and be able to implement them within a programming language; D Understand modelling and data analytic principals; E Understand some advanced topics in applied Bayesian data analysis and be able to discuss them sensibly and intelligently.
This module is delivered through formal lectures and tutorial classes.