MVE550, Stochastic processes and Bayesian inference, 2018/19

Latest news

Welcome to the course! The schedule for the course can be found in TimeEdit.

Course representatives:
Ebba Davidsson; debba (at) student.chalmers.se
Lirim Kadriu; kadriu (at) student.chalmers.se
Viktor Renberg; vikren (at) student.chalmers.se
Martin Sogno; martin.sogno (at) gmail.com

Teachers

Course coordinator: Petter Mostad

Teaching assistant: Anton Johansson

Course literature

Main textbook: Dobrow(D): Introduction to Stochastic Processes with R. Available as e-book at Chalmers. Note that R scripts used in the book (as well as some errata), are available here. Here is a list of the chapters and sections that are NOT part of the curriculum: Sections 3.9, 3.10, Section 5.5, Section 6.8, Section 7.7. Sections 8.5, 8.6. Chapter 9.

Lecture Notes(LN) on Bayesian inference will be made available via Pingpong.

We will also use one chapter (Chapter 2, about Hidden Markov Models) from Axelson-Fisk: "Comparative Gene Finding: Models, Algorithms and Implementation". This chapter will be available via Pingpong. Note: We skip the Viterbi algorithm.

Reference literature: Insua, Ruggeri, Wiper: Bayesian Analysis of Stochastic Process Models: Available as e-book at Chalmers. This book will only be used as reference.

English-Swedish mathematical dictionary

Program

Lectures

Day
Sections
Contents
Monday 5/11 10:00 - 11:45: SB-H6
D: Chapter1 + Appendices A, B, C, D.
Introduction and review.
Wednesday 7/11 15:15 - 17:00: SB-H4
LN: Chapter 1
Basics of Bayesian inference. Conjugacy.
Monday 12/11 10:00 - 11:45: SB-H4
D: Chapters 2, 3.
Markov chains.
Wednesday 14/11 15:15 - 17:00: SB-H4
D: Chapter 3
Markov chains.
Monday 19/11 10:00 - 11:45: SB-H6
Axelson-Fisk:  Chapter 2 (see Pingong. We skip the Viterbi algorithm). LN: Chapter 2
Hidden Markov Models. Inference.
Wednesday 21/11 15:15 - 17:00: SB-H4
D: Chapter 4
Branching processes
Monday 26/11 10:00 - 11:45: SB-H6
D: Chapter 5
Markov Chain Monte Carlo (MCMC) methods.
Wednesday 28/11 15:15 - 17:00: SB-H4
D: Chapter 5. LN: Chapter 3
Methods for Bayesian inference.
Monday 3/12 10:00 - 11:45: SB-H6
D Sections 5.4, 5.6.
MCMC
Tuesday 4/12 8:00 - 9:45: SB-H3
D: Chapter 6 (except 6.8).
Poisson processes.
Monday 10/12 10:00 - 11:45: SB-H4
D: Sections 7.1, 7.2, 7.3
Continuous-time Markov chains.
Wednesday 12/12 15:15 - 17:00: SB-H4
D: Sections 7.4, 7.5, 7.6
Continuous-time Markov chains.
Monday 17/12 13:15 - 15:00: SB-H4
D: Sections 8.1, 8.2, 8.3, 8.4.
Brownian motion
Tuesday 18/12 13:15 - 15:00: SB-H4
All
Review. (Please mail requests for content to Petter)

Recommended exercises

(Please do additional exercises on your own. Note that solutions to some odd-numbered exercises are available in an appendix of Dobrow).

Day
Exercises
Monday 5/11 13:15 - 15:00
ML3(Swe)-ML4(Eng)
D: Chapter 1: 6, 9, 10, 14, 16, 20, 24, 30, 32, 35
Friday 9/11 10:00 - 11:45
ML3(Swe)-ML2(Eng)
D: Chapter 1: rest of above exercises, and LN: Chapter 1: 3,4,6,7,8, (9,10).
Monday 12/11 13:15 - 15:00 ML3
Rest of above exercises, and D: Chapter 2: 2,7,10,14,16,17,18,20,21,22,26
Friday 16/11 10:00 - 11:45 SB-L408
Rest of above, and D: Chapter 3: 2, 5, 9, 14, 18, 22, 30, 35, 38, 41, 46, 64
Tuesday 20/11 8:00 - 9:45 SB-L408
Rest of above, and LN: Chapter 2: 1
Friday 23/11 10:00 - 11:45 ML4
LN: Chapter 2: Rest of exercises. D: Chapter 4: 5, 6, 8, 12, 19, 20, 26, 29.
Tuesday 27/11 8:00 - 9:45 SB-L408
D: Chapter 4: Rest of exercises.
Friday 30/11 10:00 - 11:45 SB-L408
D: Chapter 5: 2, 4, 5, 6, 8, 9, 17, 18.
Monday 3/12 13:15 - 15:00 SB-L316
D: Chapter 5: 10, 11, 12, 13, 14, 16, 20
Thursday 6/12 15:15 - 17:00 SB-L408
D: Chapter 6: 2, 5, 8, 10, 14, 16, 21, 24
Monday 10/12 13:15 - 15:00 SB-L408
D: Chapter 6: 32, 44. D: Chapter 7: 1, 4, 5, 6, 12, 14.
Friday 14/12 10:00 - 11:45 EL-43
D: Chapter 7: 18, 20, 23, 26, 30, 34, 39.
Tuesday 18/12 8:00 - 9:45 EL-43
D: Chapter 8: 1, 2, 6, 9, 16, 18.
Friday 21/12 10:00 - 11:45 SB-L408
Petter, and maybe Anton, will be available for questions and help.

Computer labs


There will be no computer labs. If necessary, specific assistance with computer-related exercises and assignments will be organized later. 

Course requirements

The learning goals of the course can be found in the course plan.

Assignments

There will be three obligatory home assignments, with deadlines Thursday 22/11, Thursday 6/12, and Thursday 20/12, at 23:55, respectively. Each assignment will be made available via Pingpong two weeks before the deadline, and your answers should be submitted via Pingpong. The assignments should be performed in groups of 2 or 3 persons. These persons should create a project group in Pingpong, and their answers should be submitted from this group. See more details in Pingpong.

Examination

The examination consists of two elements: The three obligatory home assignments and a written examination at the end. Results from these two elements are stored separately in Ladok, so they may in principle be completed in different years. Both elements must be completed to pass the course, but the passing grade is determined by the grade on the written exam. The exam will give a maximum of 30 points, with 12-17.5 points resulting in grade 3, 18-23.5 resulting in grade 4, and 24-30 points resulting in grade 5.
At the exam, the only aids allowed is a Chalmers-approved calculator.

Examination procedures

In Chalmers Student Portal you can read about when exams are given and what rules apply on exams at Chalmers. In addition to that, there is a schedule when exams are given for courses at University of Gothenburg. Before the exam, it is important that you sign up for the examination. If you study at Chalmers, you can do this from the Chalmers Student Portal, and if you study at University of Gothenburg, you sign up via GU's Student Portal.

At the exam, you should be able to show valid identification.

After the exam has been graded, you can see your results in Ladok by logging on to your Student portal.

At the annual (regular) examination:
When it is practical, a separate review is arranged. The date of the review will be announced here on the course homepage. Anyone who can not participate in the review may thereafter retrieve and review their exam at the Mathematical Sciences Student office. Check that you have the right grades and score. Any complaints about the marking must be submitted in writing at the office, where there is a form to fill out.

At re-examination:
Exams are reviewed and retrieved at the Mathematical Sciences Student office. Check that you have the right grades and score. Any complaints about the marking must be submitted in writing at the office, where there is a form to fill out.

Old exams

This is a new course, so there are no old exams. The questions at the exam will be of roughly three types: Computational examples where the theory is applied and the calculations can be done by hand or calculator, theoretical questions where you are asked to use the theory to derive some conclusions extending, exemplifying, or reproducing the theory in Dobrow, and questions surrounding how to do Bayesian inference for the models we cover.

A trial exam is available here, with suggested solutions here.

==

The course exam, on 2019-01-16, is given here, with suggested solutions here.