STATISTICS


Course Credits: 3 Units

Prerequisites: Stat 123

STAT 134 - Introduction to Bayesian Statistical Inference

Course Description

Overview and foundations of Bayesian analysis, assessment of prior distributions, posterior distributions, and predictive distributions, Bayesian inference, Bayesian hierarchical models, use of statistical software; introduction to empirical Bayes.

Course Learning Outcomes

By the end of this course, the student must be able to:

  1. Identify the basic concepts of different prior and posterior distributions;
  2. Differentiate between Bayesian and non-Bayesian framework;
  3. Demonstrate the role of prior information in Bayesian inference;
  4. Apply basic concepts in Bayesian modeling; and
  5. Interpret the results of Bayesian analysis.
Course Outline

UNIT 1. Introduction

  1. Overview of Bayesian Analysis
  2. Review of Probability
  3. Review of Inference

UNIT 2. Foundations

  1. Misuse of Classical Inference Procedures
  2. The Frequentist Perspective
  3. The Classical Perspective
  4. The Likelihood and Sufficiency Principle

UNIT 3. Bayes’ Theorem for Discrete and Continuous Models

  1. Prior Distribution
  2. Conjugate Priors
  3. Non-informative and Jeffrey’s Priors
  4. Predictive Distribution
  5. Posterior Distribution

UNIT 4. Bayesian Inference

  1. Bayesian Point Estimation
  2. Bayesian Confidence Sets
  3. Bayesian Hypothesis Testing

UNIT 5. Introduction to Hierarchical Models

  1. Definition of Hyperpriors and Hyperparameters
  2. Use of statistical software

UNIT 6. Introduction to Empirical Bayes

  1. Estimation of Hyperparameters
  2. Parametric Empirical Bayes
  3. Nonparametric Empirical Bayes