Module reading notes |
Reading notes |
Useful reading notes for the module |
|
Common distributions |
|
|
Week 1: Introduction and review of likelihood |
Lecture 1A: module overview, likelihood |
|
|
Lecture 1B: maximum likelihood estimates |
|
|
Practical 1 for IT class |
Practical tutorial for IT class |
|
R code for practical 1 |
|
|
Useful R package |
|
|
Exercise sheet 1 |
Exercise for you to practise (not to be handed in) |
|
Exercise sheet 1-solutions |
|
|
Annotated lecture slides for 29/9 |
|
|
Week 2: Bayes’ Theorem and Bayesian inference |
Lecture 2A: Bayes theorem |
|
|
Lecture 2B: Bayesian inference |
|
|
Practical 2 for IT class |
|
|
R code for practical 2 |
|
|
Data set for practical 2 |
Data set to be used in IT class for practical 2
|
|
Exercise sheet 2 (to be handed in) |
Deadline: 16th October, 11:00am |
|
Annotated lecture slides - 11/10/2023 |
The lecture slides of class 11/10 |
|
Exercise sheet 2 solutions |
|
|
Week 3: Bayesian updating/Conjugate distributions |
Lecture 3A: conjugate distributions |
Updated with review - 11/10/2023 |
|
Lecture 3B: normal example, continued |
|
|
R code for practical 3 |
|
|
Practical 3 for IT class |
|
|
Exercise sheet 3 solutions |
|
|
Exercise sheet 3 |
Exercise sheet for practice (not to be handed in) |
|
R code for exercise sheet 3 |
|
|
Annotated slides 3A, class 13/10 |
|
|
Annotated lecture slides-18/10/2023 |
|
|
Week 4: Conjugate distributions |
Exercise sheet 4 (to be handed in) |
Deadline: Monday, 30 October, at 11:00 |
|
Data set to be used in exercise sheet 4 problem 1 |
Data set to be used in exercise sheet problem 1
|
|
R code for practical 4 |
|
|
Practical 4 for IT class |
|
|
annotated slides_20/10/2023 |
|
|
Solutions to exercise sheet 4 |
|
|
Week 5: Point estimates and credible intervals |
Lecture 5A: point estimates and credible intervals |
|
|
Lecture 5B: transformed parameters, multiple parameters |
|
|
Exercise sheet 5 (not to be handed in) |
Exercise sheet for practice |
|
annotated lecture slised 25-10-2023 |
|
|
R code for practical 5 |
|
|
Practical 5 for IT class |
This practical focuses on posterior estimates and credible intervals |
|
Data set for ex sheet 5 |
|
|
Exercise sheet 5 solutions |
|
|
Week 6: Choosing a prior distribution |
Exercise sheet 6 (to be handed in) |
Deadline: Monday
the 13th November at 11am. |
|
Exercise sheet 6 dataset |
|
|
Lecture 5B: transformed parameters, multiple parameters |
|
|
Lecture 6A: Uninformative prior distributions |
|
|
Practice 6 for IT class |
|
|
R code for practical 6 |
|
|
Annotated slides_lecture_5B_transformed_parameters 1/11 |
|
|
annotated_slides_lecture_6A_uninformative prior distributions_1/11 |
|
|
Additional example on multiple parameters |
This example on multiple parameters will help you for problem 3 of exercise sheet 6 |
|
Exercise sheet 6 solutions |
|
|
R code for exercise sheet 6 |
|
|
Week 8: Informative priors, Monte Carlo integration methods and MCMC |
Lecture 8A : specifying informative prior distributions |
|
|
Lecture 8A: Monte Carlo methods |
|
|
Exercise sheet 8 (to be handed in) |
Deadline: Monday, 27th November at 11am |
|
Practical 8 for IT class |
|
|
R code for practical 8 |
|
|
Lecture 8B: MCMC |
|
|
Annotated slides 17/11 |
|
|
Annotated slides 15/11 :lecture 8A specifying informative prior distributions |
|
|
Annotated slides 15/11: lecture 8A Monte Carlo methods |
|
|
Lecture R code Monte Carlo-MCMC |
Lecture R code on Monte Carlo integration and MCMC |
|
Exercise sheet 8 solutions |
|
|
R code for exercise sheet 8 |
|
|
Week 9: MCMC |
IT class 9 |
|
|
Exercise sheet 9 (not to be handed in) |
|
|
Lecture 9A: Metropolis-Hastings MCMC |
|
|
Annotated slides 22/11: lecture 9A MCMC-Metropolis algorithm |
|
|
Lecture 9B: Metropolis-Hastings MCMC |
|
|
annotated slides 24/11 lecture 9B |
|
|
R code for exercise sheet 9 |
|
|
IT 9 class solutions |
|
|
Week 10: MCMC and posterior predictive probability |
Practical 10 for IT class |
|
|
R code for practical 10-binomial/beta |
|
|
R code for practical 10-beta/binomial (log scale) |
|
|
Exercise sheet 10 (to be handed in) |
Deadline: Monday, 11th December, 11:00am |
|
Lecture 10A: MCMC implementation issues |
|
|
Lecture 10A R code: Exponential/gamma (log-scale) |
R code for lecture 10A that implements MH on the log scale for the exponential/gamma example |
|
Lecture 10A R code: Exponential/gamma (burn in) |
R code for lecture 10A that shows how to compute the acceptance probability for different values of the proposal standard deviation and how to use burn in. |
|
Annotated slides Lecture 10A, 29/11 |
|
|
Lecture 10B: Posterior predictive probability |
|
|
annotated slides lecture 10B-1/12 |
|
|
Solutions exercise sheet 10 |
|
|
R code exercise sheet 10 |
|
|
Week 11: Posterior predictive probability and Bayes factor |
Practical 11 for IT class |
|
|
R code for practical 11 |
|
|
Lecture 11A: posterior predictive probability |
|
|
Exercise sheet 11 (not to be handed in) |
Exercise sheet on Bayes factors |
|
Annotated slides: Lecture 11A-6/12/2023 |
|
|
Lecture 11B:Bayes factors and Bayesian model selection |
|
|
annotated slides Lecture 8/12 |
|
|
exercise sheet 11 solutions |
|
|
Week 12: Revision |
Practical 12 for IT class |
|
|
R code for practical 12 |
|
|
additional exercises for the final exam |
This does not cover everything on the final! Look at the exercise sheets for other topics
|
|
Lecture 12A |
|
|
annotated lecture slides_13/12 |
|
|
annotated lectures 15/12 |
|
|
exercise sheet 12 solutions |
solutions to selected problems |
|
Past exam papers |
Exam 2020 |
|
|
Exam 2021 |
|
|
Exam 2022 |
|
|
Exam 2023 |
|