42062 - Linear Models

Learning outcomes

By the end of the course the student should know the basic theory of normal linear models and should be able to apply them to the analysis of real phenomena.

In particular the student should be able:

- to define a statistical model

- to formulate the normal linear model, estimate its parameters and test their significance

- to use variable selection procedures

- to check the validity of the assumptions the model relies upon

- to perform an anlysis of variance and interpret the results

Course contents

Multiple Linear Regression: Definition, Estimation and Hypothesis Testing. Selection of Predictor Variables in the Multiple Linear Regression Model. Normal Linear Models: Analysis of Variance.

Readings/Bibliography

- Lecture notes downloadable from Virtuale

- M.Kutner, C.J. Nachtscheim, J. Neter, W. Li, Applied linear statistical models, McGraw-Hill, 2004

 

Teaching methods

Lectures and labs using the software R

Assessment methods

Computer and oral examination.

The course Linear models is part of the integrated course Algebra and linear models. Assesment is referred to both parts and results in a single mark obtained as the average of the marks in Linear algebra and in Linear models.

Office hours

See the website of Angela Montanari