Computer intensive methods in mathematical statistics SF2955
The aim of the course is to introduce the basic
methods of bootstrap and Markov chain Monte Carlo at an intermediate level.
Techniques developed in this course have become important in large and increasing number of fields of engineering and science. The course is lectured and examined in English.
Prerequisities:
- SF 1901 or equivalent course of the type 'a first course in probability and statistics (for engineers)'
- basic differential and integral calculus, basic linear algebra,
probability theory sf2940 helpful, but not necessary.
- basic skills in writing software code for scientific computation (e.g. with Matlab).
Lecturer and Examiner : Timo Koski, Prof. homepage and contact information
Course literature
-
(1) Here is the compendium of lecture notes (GE) written by Dr. Gunnar Englund (math.stats/KTH). A hardcopy of the GE can be purchased at the studentexpedition of the Department of Mathematics, Lindstedtsvagen 15
-
(2) handout: Material to be handed out during the lectures andwill also be posted on the page
of lecture information.
The lecture notes (GE) are partly based on material from the following books:
- An Introduction to the Bootstrap, Bradley Efron and Robert Tibshirani chapters 1-14 and 20
- Computer Intensive Statistical Methods, Urban Hjorth chapters 1,2,3,5,6
- Markov Chain Monte Carlo, Gilks, Richardsson, Spiegelhalter chapters 1,2,5
Computer assignments
Instructions and information about the computer assignments (in English)
and in Swedish.
Examination:
There will be a written examination on Wednesday 25th of may, 2011, 14.00-
19.00 in V34, V35.
Registration for the written examination via "mina sidor"/"my pages"
is required.
Allowed means of assistance for the exam are a calculator (but not the manual for it!) and the two collections of Formel- och tabellsamling i matematisk statistik and in Bayesian statistics .
Each student must bring her/his own calculator to the examination. The department will distribute the
se two sets of collections of formulas. It is not allowed to use a copy of your own.
Grading
Grades are set according to the quality of the written examination.
Grades are given in the range A-F, where A is the best and F means
failed.
Fx means that you have the right to a complementary examination
(to reach the grade E).
The criteria for Fx is a grade F on the exam, and that an isolated part
of the course can be
identified where you have shown a particular lack of
knowledge and that the examination after a complementary examination on
this
part can be given the grade E.
Computer assignments are a part of the examination
There are two compulsory computer assignments which are done as homework (no scheduled computer classes).
The computer assignments are graded by P= pass or NP= not pass and do not influence the overall grade for the course.
Preliminary plan
(TK=Timo Koski GE= lecture notes)
The addresses of the lecture halls and guiding instructions are found by clicking on the Hall links below
| Day |
Date |
Time |
Hall |
Topic |
Lecturer |
| Mo |
21/03 |
10-12 |
M33
|
Lecture 1: Statistical inference and an overview of the field ch. 1 GE, handout .
|
TK |
| Wed |
23/03
|
10-12 |
M33 |
Lecture 2: Statistical inference and simulation ch.2 GE, handout
|
TK
|
Fri
|
25/03
|
10-12 |
M33 |
Lecture 3: Statistical inference ch.3 GE, handout
|
TK
|
Mon
|
28/03 |
10-12 |
M33
|
Lecture 4: Bootstrap ch. 4 GE
|
TK
|
Wed
|
30/03 |
10-12 |
M33 |
Lecture 5: Bootstrap ch. 5, ch.6 GE
|
TK
|
Fri
|
01/04 |
10-12 |
M33 |
Lecture 6: Bootstrap of arithmetic mean and of median |
TK
|
Mo
|
04/04 |
10-12 |
M33 |
Lecture 7: Estimation of bias by bootstrap ch. 8 GE |
TK
|
Wed
|
06/04 |
10-12 |
M33 |
Lecture 8: Jackknife ch. 9 GE |
TK
|
Thu
|
07/04 |
10-12 |
M33 |
Lecture 9: More complicated data structures ch. 10 GE.
|
TK
|
Wed
|
13/04 |
10-12 |
M33 |
Lecture 10: Confidence intervals, pivotal method ch. 13 GE
|
TK
|
Thu
|
14/04 |
10-12 |
M33 |
Lecture 11: Confidence intervals: precentile method. ch. 13 and 14 GE
|
TK
|
Fr
|
15/04 |
10-12 |
M33 |
Lecture 12: Tolerance intervals and bootstrap handout
| TK
|
Wed
|
27/04 |
13-15 |
M33 |
Lecture 13: Geometric representation ch. 11 GE
|
TK
|
Thu
|
28/04 |
10-12 |
M33
|
Lecture 14: bayesian methods ch.15 GE, handout |
TK
|
| Fri |
29/04 |
10-12 |
M33
|
Lecture 15: Bayesian methods ch. 15 GE, handout
|
TK
|
Mo
|
02/05 |
10-12 |
E31 |
Lecture 16:Model choice ch. 16 GE
|
TK
|
Wed
|
04/05 |
10-12 |
M33
|
Lecture 17: Model choice: cross validation ch.16 GE
|
TK
|
Fr
|
06/05 |
10-12 |
M33
|
Lecture 18: AIC and BIC ch.16 GE.
| TK
|
| Mo |
09/05 |
10-12 |
E31
|
Lecture 19: McMC: Metropolis-Hastings ch 17 GE, handout
|
TK
|
Wed
|
11/05 |
10-12 |
M33 |
Lecture 20: McMC: Metropolis-Hastings ch. 17 GE, Reversible jumps handout |
TK
|
Fr
|
13/05 |
10-12 |
M33
|
Lecture 21: Gibbs sampling ch. 17 GE |
TK
|
| Mo |
16/05 |
10-12 |
M33
|
Lecture 22: Simulated annealing ch.17 GE, handout
|
TK
|
Wed
|
18/05 |
10-12 |
M33 |
Lecture 23: Reserve, repetition |
TK
|
Fr
|
20/05 |
10-12 |
E31
|
Lecture 24: Repetition and old exams
|
TK
|
Wed
|
25/05 |
14-19 |
V34
|
EXAM
|
TK
|
Wed
|
25/05 |
14-19 |
V35
|
EXAM
|
TK
|
Welcome, I hope you will enjoy the course!
Timo
To course
web page
|
