# Generalized Linear Models (STA600)

Introduction to glm, which is a generalization of (multiple) regression for normally distributed responses to responses from a larger class of distributions, especially discrete responses. Theory for glms with application to regression for normally distributed data, logistic regression for binary and multinomial data; Poisson regression and survival analysis. Applications to data, principles of statistical modeling, estimation and inference are emphasized. Likelihood theory.

Course description for study year 2024-2025. Please note that changes may occur.

Facts

STA600

1

10

Spring

1

Spring

English

Time table

## Content

NB! This is an elective course and may be cancelled if fewer than 10 students are enrolled by January 20th for the spring semester.

Introduction to generalized linear models (GLM), which is a generalization of (multiple) regression for normally distributed responses to responses from a larger class of distributions, especially discrete responses. Theory for GLMs with application to among other tings, regression for normally distributed data, logistic regression for binary and multinomial data; Poisson regression and survival analysis. Principles of statistical modeling, likelihood theory, estimation and inference, bayesian methods. Applications and analyses of data sets are emphasized.

## Learning outcome

After having completed the course one the student should:

• Know the main theory for generalized linear models
• Know how regression with binary, multinomial, Poisson- and survival time responses may be done
• Understand use of likelihood estimation generally and especially for generalized linear models
• Be able to apply the theory in practical use on real data.

## Required prerequisite knowledge

MAT100 Mathematical Methods 1, MAT200 Mathematical Methods 2, STA100 Probability and Statistics 1
or equivalent courses.

## Recommended prerequisites

STA500 Probability and Statistics 2

## Coursework requirements

Two compulsory assigned exercises
Mandatory assignments must be passed for the student to have admittance to the exam.

Jörn Schulz

Arild Buland

## Course coordinator:

Tore Selland Kleppe

## Head of Department:

Bjørn Henrik Auestad

## Method of work

4 hours lectures and 2 hours problem solving per week.

## Open for

City and Regional Planning - Master of Science Computational Engineering - Master of Science Degree Programme Computer Science - Master of Science Degree Programme Environmental Engineering - Master of Science Degree Programme Industrial Economics - Master of Science Degree Programme Structural and Mechanical Engineering - Master of Science Degree Programme Mathematics and Physics - Master of Science Degree Programme Mathematics and Physics - Five Year Integrated Master's Degree Programme Industrial Asset Management - Master of Science Degree Programme Marine and Offshore Technology - Master of Science Degree Programme Petroleum Engineering - Master of Science Degree Programme

## Course assessment

There must be an early dialogue between the course supervisor, the student union representative and the students. The purpose is feedback from the students for changes and adjustments in the course for the current semester.In addition, a digital subject evaluation must be carried out at least every three years. Its purpose is to gather the students experiences with the course.

## Literature

Search for literature in Leganto