Search programme

​Use the search function to search amongst programmes at Chalmers. The study programme and the study programme syllabus relating to your studies are generally from the academic year you began your studies.

Syllabus for

Academic year
MVE190 - Linear statistical models
 
Syllabus adopted 2010-02-26 by Head of Programme (or corresponding)
Owner: MPENM
7,5 Credits
Grading: TH - Five, Four, Three, Not passed
Education cycle: Second-cycle
Major subject: Mathematics
Department: 11 - MATHEMATICAL SCIENCES


Teaching language: English
Open for exchange students
Block schedule: X

Course module   Credit distribution   Examination dates
Sp1 Sp2 Sp3 Sp4 Summer course No Sp
0108 Examination 7,5c Grading: TH   7,5c   19 Dec 2013 am V,  25 Apr 2014 am V,  Contact examiner

In programs

MPENM ENGINEERING MATHEMATICS AND COMPUTATIONAL SCIENCE, MSC PROGR, Year 1 (elective)
TKITE SOFTWARE ENGINEERING, Year 3 (compulsory elective)

Examiner:

Professor  Rebecka Jörnsten



  Go to Course Homepage

Eligibility:

For single subject courses within Chalmers programmes the same eligibility requirements apply, as to the programme(s) that the course is part of.

Course specific prerequisites

MVE155 Statistical Inference or a similar course

Aim

The course covers the following topics:
- multidimensional normal distributions
- general linear models in linear algebra terms
- statistical analysis of general linear models using algebraic tools like projections,
generalized matrix inverses and quadratic forms
- the duality of hypothesis tests and confidence sets
- Sheffe's and Tukey's methods for multiple tests and confidence intervals
- noncentral t- and F-distributions and their use for test power computations
- tolerance and prediction intervals
- graphical methods for model validation
- introduction to generalizations towards general heteroscedastic and covariance structures
- generalized linear models with link function for some exponential families
- estimation algorithms for various link functions.
- hypothesis testing and confidence intervals for linear combinations of parameters in
the generalized linear models: the binomial, Poisson and multinomial distribution cases
- generalized residuals and their use.

Learning outcomes (after completion of the course the student should be able to)

Build a general linear model for practical applications and perform the statistical analysis, mostly multiple linear regression by some statistical software.

Describe and analyze linear models using matrix algebra.

Content

- general linear models
in linear algebra terms
- model validation
- transformation
- interaction
- multicollinearity
- predictor selections
- generalized linear models (briefly)

Organisation

Lectures, mathematical exercises, computer labs,
practical work in groups with real data

Literature

Applied Regression Analysis 3rd ed, Draper and Smith,
Wileys series in probability and statistics

Examination

Written examination, assignments


Published: Mon 28 Nov 2016.