Recommended prerequisite for participation in the module

Content, progress and pedagogy of the module

The aim of the course is for students to gain experience and understanding of Bayesian statistics, simulation based statistical inference and how to implement simulation based Bayesian inference in practice on a computer.

Learning objectives

Knowledge

• has knowledge of the Bayesian principle including (conjugate) priors

• has knowledge of algorithms used for Bayesian inference such as e.g. the Gibbs sampler and the Metropolis-Hastings algorithm

• has knowledge of the theory of Markov chain Monte Carlo methods such as e.g. irreducibility, aperiodicity and invariant densities

• has knowledge of practical challenges when using simulation based inference such as e.g. tuning, acceptance rates and burn-in

Skills

• can apply the relevant methodologies from the course to conduct a Bayesian analysis of a given data set

• can state the underlying assumptions and argue about limitations and extensibility of the chosen methodologies

Competences

• can implement a relevant algorithm from the course to conduct simulation based Bayesian inference

Type of instruction

The teaching is organised in accordance with the general form of teaching in the curriculum, re. § 17.

Extent and expected workload

This is a 5 ECTS project module and the work load is expected to be 150 hours for the student.

Exam

Exams