Note: This course is called MVE185 at Chalmers

The course is built around statistical models and computational tools in cases where computer-assisted computations are essential. In particular, we focus on stochastic simulation as a computational tool. Bayesian inference is a central concept, and we will study Markov chain Monte Carlo simulation methods from both applied and theoretical viewpoints. Jackknife and bootstrap methods will be studied, as well as decision theory. Permutation methods for hypothesis testing and multiple hypothesis testing issues are also covered in this course.

A special effort will be made to help the student to see the connections and interplay between statistical modeling and applied problem solving, as well as computational and theoretical aspects of the models.

The course gives 7.5 hp.

Latest news

2008 – 11 – 05: The exam has now been graded, and a set of suggested solutions is available.

2008 – 09 – 16: Some changes in contents of lectures and exercise sessions (Chapter 11 removed)

2008 – 09 – 11: Some specifications of exercises added.

2008 – 09 – 01: IMPORTANT CHANGE: The Tuesday exercises have been switched with the Friday lectures.

2008 – 08 – 25: Update of this homepage

2008 – 06 – 04: This homepage has been extensively updated.  

Examiner and lecturer

Petter Mostad 

Exercises: Dmitrii Zholud

 

Course literature

Textbook

Jim Albert: Bayesian computation with R. The book has been ordered at the Cremona bookstore.

The following subjects will also be covered. Teaching material for these subjects will be handed out later:

• Bootstrapping, jackknifing, and partition methods.
• Permutation methods for hypothesis testing.
• Multiple testing issues.

A recommended book for reading additional Bayesian theory is Gelman et al: Bayesian Data Analysis, second edition.

Plan for lectures and classes

Time	Place	Contents	Teacher
Tues Sep 2, 10:00 – 11:45	MVH12	Lecture: Chapter 1. Presentation of R (handouts)	Petter Mostad
Tues Sep 2, 15:15 – 17:00	MVF21	Lecture: Chapter 2. Presentation (handouts)	Petter Mostad
Fri Sep 5, 10:00 – 11:45	MVF25	Exercises: Chapter 1: 1,2,3,4. Chapter 2: 1,2,5. Solutions Chapter 1. Solutions Chapter 2.	Dmitrii Zholud
Tues Sep 9, 10:00 – 11:45	MVH12	Lecture: Chapter 3	Petter Mostad
Tues Sep 9, 15:15 – 17:00	MVF21	Lecture: Chapter 4	Petter Mostad
Fri Sep 12, 10:00 – 11:45	MVF25	Exercises: Chapter 3: 2,3,4. chapter 4: 1,2. Solutions Chapter 3. Solutions Chapter 4.	Dmitrii Zholud
Tues Sep 16, 10:00 – 11:45	MVH12	Lecture: Chapter 5	Petter Mostad
Tues Sep 16, 15:15 – 17:00	MVF21	Lecture: Chapter 6	Petter Mostad
Fri Sep 19, 10:00 – 11:45	MVF25	Exercises from Chapter 5. Suggested solutions.	Petter Mostad
Tues Sep 23, 10:00 – 11:45	MVH12	Lecture: Chapter 6. Presentation of possible student projects.	Petter Mostad
Tues Sep 23, 15:15 – 17:00	MVF21	Lecture: Chapter 6	Petter Mostad
Fri Sep 26, 10:00 – 11:45	MVF25	Exercises from Chapter 6	Dmitrii Zholud
Tues Sep 30, 10:00 – 11:45	MVH12	Lecture: Bootstrapping. Deadline for choice of student projects.	Petter Mostad
Tues Sep 30, 15:15 – 17:00	MVF21	Lecture: Questions and answers.	Petter Mostad
Fri Oct 3, 10:00 – 11:45	MVF25	Help with any R problems connected to course work. Exercises about bootstrapping.	Dmitrii Zholud
Tues Oct 7, 10:00 – 11:45	MVH12	Lecture: Chapter 7	Petter Mostad
Tues Oct 7, 15:15 – 17:00	MVF21	Lecture: Chapter 8	Petter Mostad
Fri Oct 10, 10:00 – 11:45	MVF25	Help with R problems connected to course work. Exercises: Chapter 7, ex. 1,2. Chapter 8, ex. 1.	Dmitrii Zholud
Tues Oct 14, 10:00 – 11:45	MVH12	Lecture: Multiple testing issues (Handouts)	Petter Mostad
Tues Oct 14, 15:15 – 17:00	MVF21	Lecture: Permutation methods	Petter Mostad
Thurs Oct 16, 13:15 – 17:00	MVH11	Presentations of student projects	Petter Mostad
Fri Oct 17, 10:00 – 11:45	MVF25	Help with any R problems connected to course work. Exercises.	Dmitrii Zholud
Tues Oct 21, 15:15 – 17:00	MVF21	One student presentation. Review of course. Course evaluation.	Petter Mostad
Sat Oct 25, 8:30 – 13:30	Väg och Vatten (next to Arkitektur on the map)	Written exam	Petter Mostad

Computer labs

Examination

To pass this course you must pass the written exam and make a project presentation.

Written examination

IMPORTANT NOTE: You need to sign up for the exam, separately from signing up for the course. You do this a couple of weeks befor the exam, on a list that is posted outside our departments Expedition office.

During the exam the following aids are permitted: A calculator. Bring ID and receipt for your student union fee.

Solutions to the exam will be published on this homepage after the exam.
You will be notified the result of your exam by email from LADOK (This is done automatically as soon as the exams have been marked an the results are registered.)
The exams will then be kept at the students' office in the Mathematical Sciences building.
Check that the number of points and your grade given on the exam and registered in LADOK coincide.
Complaints of the marking should be written and handed in at the office. There is a form you can use, ask the person in the office.

The following link will tell you all about the examination room rules at Chalmers, applicable for this exam: Examination room instructions

The course is currently given each year in September/October in Chalmers reading period 1. In addition to the ordinary exam after each course, there are up to two re-exams each year, one in January and one in August.

Project presentation

Towards the middle of the course, students will choose individual projects from a list of possible projects. Each project will consist of some question or questions, together with data illuminating these questions. It is also possible for students to use their own questions and data, after approval. The analysis of the data should include one or more of the computer intensive methods covered in the course. Towards the end of the course, each student should make a 15 minute oral presentation, which should include a discussion about the modelling and computational choices made, and a discussion about the interpretation of the results.

Old exams

As this is a new course, there are no old exams.

However, there is a trial exam, with some examples of possible questions. There is also a set of suggested solutions.