MAS8303, Modern Bayesian Inference
Semester 1, 2012-13
MAS8303 students should "Bookmark" this page.
Timetable
Times and locations of classes are as follows.
============================================================================
Day Time Room Class
============================================================================
Monday 9-11 Herschel TR1 Lecture/Tutorial
Tuesday 11-1 Herschel TR1 Lecture
Thursday 4-5 Bedson Teaching Centre 2.40 Practical/Tutorial
============================================================================
It will be necessary to use both hours on Mondays as lecture time in some weeks but not every week. When it is not used for lecture it can be used as tutorial time.
I have allocated 12-1 and 2-3 on Mondays as "Office Hours" for this module. If this is not a good time because of other classes, please let me know and I will try to find a better time.
An attendance register will be taken at each problem or practical class. Please note
that a good attendence record will be taken into account when deciding
whether to pass students with borderline assignment/exam marks.
Lecture notes
![[Get Acrobat Reader]](http://www.adobe.co.uk/images/getacro.gif)
Lecture notes will be posted below, together with solutions to
problems. Extra lectures will be added to the notes as they are written. They are in pdf format and you will need Adobe Reader to view them - click on the link to download your own (free) copy.
Assessment
The assessment of the module consists of a 2-hour examination at the end
of Semester 2 (50%), 4 sets of assessed problems (20% in total: 5% each) and two tests (30% in total: 15% each).
The test for Part 2 of the module will be in Week 11.
- Specimen examination questions for my part of the module, in the actual exam format, are available
here.
- The examination papers for 2009-10 and 2010-11 are available from the University's
past exam papers site. (I do not know why the 2011-12 paper is not there).
- The formula pages which were given in the examination paper for 2011-2 are available
here.
- The solutions to my questions on the 2011-12 examination paper are available here.
- The test for my part of the module in 2011-2 is available here and the solutions are
here.
- The test for my part of the module in 2012-3 with solutions is
here.
This module contains tests worth more than 10% for which rescheduling can be
requested (by means of submitting a PEC form). For other coursework it is not
possible to extend submission deadlines and no late work can be accepted. For details
of the policy (including procedures in the event of illness etc.) please look at the
School web site.
Data
- Leukaemia survival: data.
- Problems 4 (2012-13), Question 2: R function to read
piston ring data.
- Problems 4 (2012-13), Question 3: R function to read
fraud data.
- Problems 3 (2012-13), Question 2: Surgery
data.
- Problems 3 (2012-13), Question 3: Barley yield
data.
- Problems 3 (2010-11), Question 2: Insulation
data.
- Problems 3 (2010-11), Question 3: Protein
data.
- Lung disease data: Lung
data.
- Sales data: Sales
data.
- Abrasion loss
data.
- Butter fat
data.
- Heights and weights of eleven-year-old girls:
data.
- Salinity measurements (Bimini):
data.
- Aircraft fatalities example:
data.
- IBM stock price:
data.
- Simulated mixture:
data.
- Time intervals between eruptions of ``Old Faithful'' geyser:
data.
- Logs of time intervals between eruptions of ``Old Faithful'' geyser (for use with rjags):
data.
- Logs of time intervals between eruptions of ``Old Faithful'' geyser (for use with R function):
data.
- Road vehicle headways (1st set) (for use with rjags):
data.
- Road vehicle headways (1st set) (for use with R function):
data.
- Road vehicle headways (2nd set):
data.
- Deaths in surgery:
surgicaldata.
- Data for epilepsy example:
epilndata
epilxdata
epilydata.
- Data for rats example (Practical 5):
ratsxdata
ratsydata.
- Data for Exercise 4.5
here.
- Chemical paste
data.
- Down's syndrome data.
- Pollution and respiratory illness
data.
- Teaching methods
data.
- Hardness of timber
data.
- Yields of carrots
data.
Information on R and BUGS/rjags
An Introduction to R can be downloaded
here.
The WinBUGS manual can be downloaded
here.
Here is a list of functions and distributions available in BUGS,
- R function for linear models: linmod.
- R function for several normal samples, conjugate prior: oneway.
- R function for two-state hidden Markov model with normal components: hmmnorm.
- R function for ``Headways'' hidden Markov model: hmmheadway.
- BUGS model for ``Babies'' example: babiesbug.
- BUGS model for ``Tonsils'' example: tonsilsbug.
- BUGS model for ``Abrasion loss'' example with missing data: abmissbug.
- BUGS model for integrated moving average IMA (0,1,1) process: imabug.
- BUGS model for simulated normal mixture: mixturenormbug.
- BUGS model for ``Old Faithful'' log intervals (normal mixture): faithnormbug.
- BUGS model for ``Old Faithful'' intervals (gamma mixture): faithgammabug.
- BUGS model for ``Old Faithful'' log intervals (normal HMM): faithnormhmmbug.
- BUGS model for ``Old Faithful'' intervals (gamma HMM): faithgammahmmbug.
- BUGS model for vehicle headways (independent): headway0bug.
- BUGS model for vehicle headways (HMM): headway3bug.
- BUGS model for rats example (Practical 5): ratsbug.
- BUGS model for pollution and respirartory illess: model11a.
Initial value files:
December 2012 Test
January 2013 Test
Please report to me any
errors or suggested improvements to these notes.