Introduction to Bayesian Statistics (MA4740)

Course Contents

• Bayes’ theorem, prior and posterior distributions, conjugate priors, Bayesian inference for single and multi-parameter models, posterior intervals, posterior predictive distribution, Markov chain Monte Carlo (MCMC), Metropolis-Hastings algorithm, Gibbs sampling, convergence diagnostics, Bayesian hypothesis testing, Bayesian regression and classification.

What you'll learn

Bayesian Statistics is a key topic in modern statistical science. It provides principled ways of combining prior information with data at hand. The objective of this course is to explore Bayesian inference techniques and discuss their application in real-life problems. Students will learn how to formulate a scientific question by constructing a Bayesian model and performing Bayesian statistical inference to answer that question. Throughout this course, students will be exposed to the theory of Bayesian inference and will learn several computational techniques, such as Markov Chain Monte Carlo (MCMC) algorithms, and use these techniques for Bayesian analysis of real data.

About the Instructor

Dr. Arunabha Majumdar, accompanied by teaching assistants from the Department of Mathematics.

Instructor Profile

Course Assessment

Assessment may consist of assignments and/or quizzes and/or viva and/or exams.