Graduate Course in Statistical Computing, Spring/Fall 2005

Summary

The course aims to give graduate students in statistics a background in computational methods that are relevant for understanding and applying computation-based statistical methodology.

The course is primarily aimed at graduate students in different branches of statistics. Pre-requisites include a basic course in statistical inference plus computing experience, preferably programming experience. Other participants are welcome, provided they have the stated prerequisites.

Evaluation of the students' weekly assignments will serve for examination. A total of 5 credit points are awarded conditional on carrying out 75% of the weekly assignments. Credit points can be awarded separately for the two parts of the course (see below).

Part I: Computational Tools

Part II: Computational Statistics

(3 credits) This part will cover boostrapping, Markov Chain Monte Carlo (MCMC) methods, and the Expectation-Maximization (EM) algorithm.

The course will start on September 6th, 14:00, in Room Wargentin at the Department of Medical Epidemiology and Biostatistics on the KI North campus (MEB). Lectures will take place Tuesday afternoons during September and October, ending on October 25th.

Lecture September 6, 2005: Organization of Part II Presentation Assignments R Examples Score data for R Examples Handins

Lecture September 13, 2005: Presentation Assignments R Examples Lutenizing hormone data

Lecture September 20, 2005: Presentation Assignments R Examples Handins

Lecture September 27, 2005: Assignments

Lecture October 4, 2005: Assignments

Lecture October 11, 2005: Assignments

Lecture October 18, 2005: Assignments

Registration

Literature and Software

No single book will cover the whole lecture. We will make use of selected reference papers and lecture notes. Recommended for additional reading:

• B. Efron and R.J. Tibshirani. An Introduction to the Bootstrap. Chapman and Hall, 1993.
• W.R. Gilks, S. Richardson, and D.J. Spiegelhalter. Markov Chain Monte Carlo in Practice. Chapman and Hall, 1996.
• W. Kennedy and J.E. Gentle. Statistical Computing. Dekker, 1980.
• K. Lange. Numerical Analysis for Statisticians. Springer, 1999.
• G.J. McLachlan and T. Krishnan. The EM Algorithm and Extensions. Springer, 1996.
• W.H. Press, S.A. Teukolsky, W.T. Vetterling, and B.P. Flannery. Numerical Recipies in Fortran 77. Cambridge University Press, 2nd edition, 1992.

The main computing environment for the course will be the free statistical software R.