Course info

STA 402: Bayesian Inference and Decision Theory

 In this course, you will be introduced to the Bayesian approach to inference—a framework that not only allows us to update our beliefs in light of new evidence but also provides powerful tools for decision-making under uncertainty.  Unlike the traditional frequentist methods, you may have seen in earlier courses, Bayesian methods integrate prior knowledge with observed data, leading to flexible and practical solutions in real-world problems. Together, we will explore: Bayes’ theorem and the role of prior and posterior distributions, Bayesian estimation and testing through loss and risk functions, Properties of Bayes estimators and credible sets, Simulation methods for probability distributions and posterior analysis, And the principles of Decision Theory, including the minimax principle, Bayes decision rules, and statistical games. The course will blend theory and practice. You will learn mathematical foundations through lectures and readings, but also apply these ideas through labs in R, case studies, group discussions, and presentations. By the end, you should be able to both explain the theory and apply Bayesian methods to practical problems in fields like medicine, economics, and machine learning. I encourage you to approach this unit with curiosity and an open mind. Bayesian statistics is not just about solving equations—it is about thinking probabilistically and making rational choices in the face of uncertainty. I look forward to an exciting and intellectually rewarding semester with you.

 

Warm regards,

Nathan Musembi

Course Instructor – STA 402