You are currently viewing the 2018 version of this course. Change to 2019

Subject details

Students who successfully complete this subject will be able to:

  1. Differentiate important distributions commonly used in Bayesian Statistic
  2. Defend the importance of concepts such as Prior Distributions and Posterior Distributions in Bayesian Statistical Modeling
  3. Describe the importance of Markov Chain Monte Carlo simulation in Bayesian Analysis
  4. Develop programming capabilities to perform Bayesian analysis
  5. Evaluate empirical applications of Bayesian analysis in an appropriate software environment
  6. Articulate the differences between Bayesian estimation and maximum likelihood estimation
  7. Argue the merits of Bayesian methodology.
    • Bayes theorem and the concept of Bayesian statistics
    • Distributions often used in Bayesian statistics
    • Prior distributions, likelihood functions, and posterior distributions
    • Bayesian estimation and model fitting using appropriate software
    • Differences between Bayesian estimation and maximum likelihood estimation
    • Choice of prior distribution
    • Empirical Bayes estimation
    • Bayesian hierarchical models
    • Empirical applications of Bayesian analysis using appropriate software
  • Study resources

    • Instructional methods

      • Discussion forum/Discussion Board
      • Online Quizzes/Tests
      • Online assignment submission
      • Podcasting/Lecture capture
      • Standard Media
      • Web links
    • Print materials

      • Welcome letter

You must have successfully completed the following subject(s) before starting this subject:

SWI-STA60003-Basic Statistical Computing Using R , or SWI-HMS772

Special requirements

No special requirements

The subject introduces the fundamentals of Bayesian statistical modelling. Students will learn the importance of subjective beliefs in Bayesian statistics. Important concepts such as prior distributions, likelihood functions, and posterior distributions will be discussed at length. Numerical estimation techniques, such as Metropolis-Hastings and Gibbs sampling, will be introduced. Empirical applications of Bayesian analysis will be performed in an R software environment.

Please note: assessment values are indicative only, details will be advised at the start of the subject.
 

  • Assignments — 2 (40%)
  • Invigilated Exam (50%)
  • Quizzes — Online (10%)

Textbook information is pending.

Related degrees