Generalised Linear Models

7.5 credits

Syllabus, Master's level, 1MS019

This course has been discontinued.

A revised version of the syllabus is available.

Code: 1MS019
Education cycle: Second cycle
Main field(s) of study and in-depth level: Mathematics A1N
Grading system: Fail (U), Pass (3), Pass with credit (4), Pass with distinction (5)
Finalised by: The Faculty Board of Science and Technology, 3 November 2008
Responsible department: Department of Mathematics

Entry requirements

120 credit points including Analysis of Regression and Variance

Learning outcomes

In order to pass the course (grade 3) the student should

have acquired a good overview of linear statistical models and their generalisations;

be acquainted with the theory of generalised linear models;

be able to use models with various link functions and link distributions such as models for discrete data;

be able to perform binary logistic regression and analysis of contingency tables;

be familiar with log-linear models;

be familiar with quasi-likelihood methods;

be able to analyse a given set of data using generalised linear models;

have experiences of practical examples from various areas of applications, especially medical applications.

Content

Linear statistical models, generalised linear models. Likelihood-based inference. Models for discrete data. Logistic regression. Analysis of contingency tables. Introduction to log-linear models. Estimation and model fitting. Residual analysis. Quasi-likelihood methods. Practical examples from different application areas with emphasis on medical applications.

Instruction

Lectures, problem solving sessions and computer-assisted laboratory work.

Assessment

Written examination at the end of the course. Compulsory assignments and laboratory work during the course.