BAYESIAN STATISTICS - 2020/1
Module code: MAT3003
In light of the Covid-19 pandemic, and in a departure from previous academic years and previously published information, the University has had to change the delivery (and in some cases the content) of its programmes, together with certain University services and facilities for the academic year 2020/21.
These changes include the implementation of a hybrid teaching approach during 2020/21. Detailed information on all changes is available at: https://www.surrey.ac.uk/coronavirus/course-changes. This webpage sets out information relating to general University changes, and will also direct you to consider additional specific information relating to your chosen programme.
Prior to registering online, you must read this general information and all relevant additional programme specific information. By completing online registration, you acknowledge that you have read such content, and accept all such changes.
The module looks at the branch of statistics called Bayesian Statistics. It relies on subjective probability and looks at why this is extremely useful for modelling realistic problems. The module covers an introduction to Bayesian statistics, incorporating prior to posterior analysis for a wide range of statistical models. This shows the students an alternative approach to the Classical statistics that they have studied so far and looks at various statistical techniques that they have studied before and gives them a Bayesian approach.
SANTITISSADEEKORN Naratip (Maths)
Number of Credits: 15
ECTS Credits: 7.5
Framework: FHEQ Level 6
JACs code: G300
Module cap (Maximum number of students): N/A
Prerequisites / Co-requisites
MAT2013 Mathematical Statistics
Indicative content includes:
- review of distribution theory
- subjective probability and prior distributions – noninformative and conjugate
- prior to posterior analysis
- exponential families, sufficiency and conjugate priors
- predictive inference
- Bayesian estimation and hypothesis testing
- application to linear models
- approximate methods to estimation
- elements of decision theory and comparative inference
|Assessment type||Unit of assessment||Weighting|
|School-timetabled exam/test||CLASS TEST (50 MINS)||20|
|Examination||EXAMINATION - 2 HOURS||80|
The assessment strategy is designed to provide students with the opportunity to demonstrate:
· Understanding of and ability to interpret and manipulate mathematical statements.
· Subject knowledge through the recall of key definitions, theorems and their proofs.
· Analytical ability through the solution of unseen problems in the test and exam.
Thus, the summative assessment for this module consists of:
· One two hour examination at the end of Semester 2; worth 80% module mark.
· One 50 minute in-semester test; worth 20% module mark.
Formative assessment and feedback
Students receive written feedback via a number of marked coursework assignments over an 11 week period. In addition, verbal feedback is provided by lecturer at biweekly tutorial lectures.
- introduce the rationale for, the main techniques of, and general issues in Bayesian statistics
- apply techniques to standard statistical models, including exponential families and linear models
- apply Bayesian approaches to estimation and testing
- introduce Bayesian prediction
- consider the role of decision theory
|1||Analyse the differences between the Bayesian paradigm and frequentist statistical methods||KC|
|2||Calculate the posterior and predictive distribution and related quantities||KC|
|3||Define hierarchical models and state and prove related theorems||KC|
|4||Demonstrate how models can be written in hierarchical form and calculate posterior quantities||KCPT|
|5||Explain the arguments for and against the Bayesian paradigm.||KC|
C - Cognitive/analytical
K - Subject knowledge
T - Transferable skills
P - Professional/Practical skills
Overall student workload
Independent Study Hours: 117
Lecture Hours: 25
Seminar Hours: 8
Methods of Teaching / Learning
The learning and teaching strategy is designed to provide:
- A detailed introduction to the theory behind, methodology and approaches used in Bayesian statistics
- Experience (through demonstration) of the methods used to interpret, understand and solve problems in analysis
The learning and teaching methods include:
3 x 1 hour lectures per week x 6 weeks and 2 x 1 hour lectures per week for 5 hours, with additional notes on white board to supplement the module handbook and Q + A opportunities for students.
5 x 1 hour tutorial replaces one of the lectures for guided discussion of solutions to problem sheets provided to and worked on by students during the tutorial.
Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.
Reading list for BAYESIAN STATISTICS : http://aspire.surrey.ac.uk/modules/mat3003
Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2020/1 academic year.