[Skip navigation]

[LU]

Monte Carlo and Empirical Methods for Stochastic Inference, VT-18

Overview

Current information:

This item will be continuously updated during the course.

Lectures:

Tuesdays 15-17, E:C
Thursdays 10-12, E:1406 (reading week 1)
Thursdays 8-10, E:1406 (reading week 2-7)
See also the schedule below

Computer sessions for projects: (Reading week 2--7)

Wednesdays in E:Neptunus, E:Pluto choose either 8-10 or 15-17. Sign up link available above (from reading week 1).

For those of you who are new to matlab:
Introduktion till Matlab (in Swedish)
Introduction to Matlab (Mathworks)
Matlab to R reference

Office hours:

(Reading week 2--7)
Friday 15:30-16:30, MH:130 (MW), MH:138A (MJ) and MH:326 (SW)

Examination

Three home assignments/projects and an oral exam after the last project.
The assignments will be handed out during the 2nd, 4th, and 6th course week.
The Questions for the oral exam are now available here.

Schedule

Day Lectures (chapters in the book) Home assignments PDF
w1Tue16/1L1 Introduction, the Monte Carlo (MC) method (1, 6.1)
R. Echhardt (1987) Stan Ulam, John von Neumann, and the Monte Carlo method
Rules for Canfield Solitaire
L1 pdf
Thu18/1L2 MC (cont.), Random number generation (6.1-6.2)
How things are done in MATLAB
Uniform random numbers pre v. 5
Random Number Generators: Good Ones Are Hard To Find, Parker and Miller (1998)
Ziggurat algorithm for Gaussian distribution Mersenne twister article C-code Mersenne twister
L2 pdf

Proof of inversemethod pdf
w2Tue23/1L3 MC (cont.), random number generation (cont.) (6.4.1)HA1 out(HA1, powercurve) L3 pdf
Wed 8-10 24/1C1
Wed 15-1724/1C1
Thu25/1L4 Random number generation (cont.), variance reduction (6.4.2-6.4.3) L4 pdf
w3Tue30/1L5 Sequential Monte Carlo (SMC) methods (6.3) L5 pdf
Wed 8-1031/1C2
Wed 15-1731/1C2
Thu1/2L6 SMC methods (cont.)L6 pdf
w4Tue6/2L7 SMC methods (cont.)
A key paper on SMC: Gordon et al. (1993)
HA1 in (6/2 15:00)
HA2 out pdf
L7 pdf
Wed 8-107/2C3
Wed 15-177/2C3
Thu8/2L8 Markov chain Monte Carlo (MCMC) (7)
Two key papers on MCMC: Metropolis et al. (1953)
Hastings (1970)
L8 pdf
w5Tue13/2L9 MCMC (7.1)
L9 pdf
Part of proof of LLN pdf
Wed 8-1014/2C4
Wed 15-1714/2C4
Thu15/2L10 MCMC (7.2)
Some implementation tips for MCMC Metropolis-Hastings samplers: MH_tips
L10 pdf
w6Tue20/2L11 Stochastic modelling and Bayesian inference,
MCMC for Bayesian computation (7.2-7.3)
HA2 in (20/2 15:00)
HA3 out pdf
Data and files for HA3 coal_mine_disasters.mat,atlantic.txt,est_gumbel.m
L11 pdf
Wed 8-1021/2C5
Wed 15-1721/2C5
Thu22/2L12 Statistical models L12 pdf
w7Tue27/2L13 Bootstrap (9)
A leisurely look at the Bootstrap, the Jackknife,
and Cross-Validation (1983)
L13 pdf
Wed 8-1028/2C6
Wed 15-1728/2C6
Thu1/3L14 Bootstrap (cont), Permutation tests (9.8) L14 pdf
w8Tue6/3 HA3 in (6/3 15:00)

Literature

Geof H. Givens and Jennifer A. Hoeting Computational Statistics Second Edition (2012) The course book is now available as an ebook: Computational Statistics by Geof H. Givens and Jennifer A. Hoeting
You can also look at the Book homepage to download the data used in the book.

The above book is the only one needed for the course.
However if you wish to explore other literature some good options are:

Monte Carlo

Bootstrap

People

Course administrator/lecturer:

Magnus Wiktorsson
room: MH:130
phone: 046-222 86 25
e-mail: magnusw@maths.lth.se

Computer sessions:

Maria Juhlin
room MH:138A
e-mail: juhlin@maths.lth.se

Samuel Wiqvist
room MH:326
phone: 046-222 79 83
e-mail: samuel@maths.lth.se