SC7/SM6 Bayes Methods HT20
lectures in LLT.
Part C classes: see dept webpage
MSc classes: see canvas pages.
MSc practical sessions: see canvas pages.
Lecture schedule and slides
following schedule is a sketch to give you a sense of where we are going. The
material from last
is available here. I do not promise to stick to this
schedule. It is correct only as a record.
Week 1 – common ground I
The Bayesian inferential pipeline - slides
Case Study – radiocarbon dating – slides
(for later main
Week 2 – common ground II
Markov Chain Monte Carlo I – slides
for this and next lect.
Markov Chain Monte Carlo II – slides
Week 3 – back to the basics (in L6)
Data Augmentation; Estimating Bayes Factors – slides
Decision theory; Utility and the expected-utility hypothesis – slides
Week 4 - principles
Coherence and the Savage axioms - slides
(sorry still no page numbers)
Exchangeability and de Finetti’s Theorem - slides
Week 5 – Approximate Bayesian Computation
ABC - slides
Model averaging - slides
Week 6 – the number of unknowns is unknown
MCMC with involutions and Jacobians - slides
(slight changes after lecture)
Reversible Jump MCMC – slides
Week 7 – the number of unknowns is infinite
Reversible Jump MCMC case study; Bayesian Non-Parametric Models (intro) slides
(the slides for L13 and the code in L12.R
were updated 6/3/20 – fix missing m! in the posterior).
Bayesian Non-Parametric models: Dirichlet-Process slides
Week 8 – approximations
Chinese Restaurant Process; Normal-Dirichlet mixture;
Galaxy data revisited - slides
Gibbs sampler for DP mixture (Galaxy data, cont);
Laplace Approximation; slides
(the Laplace approximation material was
covered briefly but is not examinable)
Week 3: first
Week 5: second
Week 7: third
problem sheet and related R-code
for optional questions
Week 1 TT20: fourth
MSc Lab sessions
Week 2: practical
- Bayesian inference for a thumbtack experiment (solutions
Week 5: practical
– (marked with feedback) with solutions
to Q1, chess
data and CompRank data.
Week 7: practical
– ABC for a variable dimension model of change points (R-file
Mock Exam Questions – correction mock 2 Q1(b) posted 19/05/20
are some mock exam questions: Mock 1;
Here are sample solutions to M1 and M2.
question should take approximately 45 minutes. MSc and Part C exams from 2017
available on OXAM (on weblearn).
1. C.P. Robert, “The Bayesian Choice: From
Decision-Theoretic Foundations to Computational
2nd edition, Springer, 2001
2. C.P Robert & G Casella, “Monte Carlo
Statistical Methods”, 2nd edition, Springer, 2004
3. A. Gelman et al, “Bayesian Data
Analysis”, 3rd edition, Boca Raton Florida: CRC Press, 2014