Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: THEend8_
MATH3871 / MATH5960
Bayesian Inference and Computation
Course Aims
? Provide a strong background in the concepts and philosophy of Bayesian inference.
? Instil an appreciation of the benefits of the Bayesian framework.
? Provide extensive practical opportunities to implement Bayesian data analyses.
? Present an overview of research activity in this field.
Course Description
After describing the fundamentals of Bayesian inference, this course will examine the specification
of prior and posterior distributions, Bayesian decision theoretic concepts, the ideas behind
Bayesian hypothesis tests, model choice and model averaging, and evaluate the capabilities of
several common model types, such as hierarchical and mixture models. An important part of
Bayesian inference is the requirement to numerically evaluate complex integrals on a routine
basis. Accordingly, this course will also introduce the ideas behind Monte Carlo integration,
importance sampling, rejection sampling, Markov chain Monte Carlo samplers such as the Gibbs
sampler and the Metropolis-Hastings algorithm and use of the WinBuGS posterior simulation
software.
Late Submission of Assessment Tasks
A late penalty of 5% of the awarded mark will be applied per day or part day any assessment task
is submitted more than 1 hour late. (Where "late" in this context means after any extensions
granted for Special Consideration or Equitable Learning Provisions.) For example, an assessment
task that was awarded 75% would be given 65% if it was 1-2 days late. Any assessment task
submitted 7 or more days late will be given zero.
Note that the penalty does not apply to
? Assessment tasks worth less than 5% of the total course mark, e.g. weekly quizzes,
weekly class participation, or weekly homework tasks.
? Examinations and examination-style class tests
? Pass/Fail Assessments
Course Schedule
The course will include material taken from some of the following topics. This is should only serve
as a guide as it is not an extensive list of the material to be covered and the timings are
approximate. The course content is ultimately defined by the material covered in lectures.
Weeks Topic Reading (if
applicable)
1 Introduction to subjective probability and differences
between Bayesian and classical statistics
Refer to Moodle
2 Prior and posterior distributions Refer to Moodle
3 Point estimation, interval estimation and predictive
distributions
Refer to Moodle
4 Bayesian analysis of normal models Refer to Moodle
5 Introduction to Monte Carlo methods Refer to Moodle
7 MCMC methods Refer to Moodle
8 Bayesian hypothesis testing Refer to Moodle
9 Linear and generalised linear models Refer to Moodle
10 Hierarchical models Refer to Moodle
Textbooks
Course Learning Outcomes (CLO)
? Provide a background in the concepts and philosophy of Bayesian inference.
? Demonstrate an understanding of how common model type’s work and be able to construct
models for new problems.
? Show an appreciation of the importance of computational techniques in Bayesian
inference.
? Perform real-world Bayesian data analyses.
Moodle
Log in to Moodle to find announcements, general information, notes, lecture slide, classroom tutorial
and assessments etc.
The School of Mathematics and Statistics has adopted a number of policies relating to enrolment,
attendance, assessment, plagiarism, cheating, special consideration etc. These are in addition to
the Policies of The University of New South Wales. Individual courses may also adopt other
policies in addition to or replacing some of the School ones. These will be clearly notified in the
Course Initial Handout and on the Course Home Pages on the Maths Stats web site.
Students in courses run by the School of Mathematics and Statistics should be aware of the School
and Course policies by reading the appropriate pages on the Maths Stats web site starting at
The School of Mathematics and Statistics will assume that all its students have read and
understood the School policies on the above pages and any individual course policies on the
Course Initial Handout and Course Home Page. Lack of knowledge about a policy will not be an
excuse for failing to follow the procedure in it.