Course: Linear Models

Course type: compulsory
Lecturer: Katarina Košmelj, Ph.D., Full Professor

Study programme and level Study field Academic year Semester
Applied statistics, second level All modules 1st 1st

For the timeline see Curriculum.


  • Enrolment into the first year of the programme.
  • Prerequisites to the written exam are the successfully completed homeworks.

Content (Syllabus outline):
Simple linear regression:

  • Assumptions, parameter estimation, statistical inference. Analysis of variance and regression. Regression through the origin.
  • Diagnostics:  analysis of residuals, analysis of special points.
  • Useful transformations.


  • The difference between regression and correlation model, different correlation coefficients.

Multiple regression:

  • parameter estimation, statistical inference;
  • diagnostics, multicollinearity;
  • descriptive variables in the model, model with multiple regression lines;
  • polinomial model;
  • complex linear models.
  • Nonlinear models.
  • Modelling of covariance structure (gls models).
  • Linear mixed models.
  • Objectives and competences:
    Linear models are basic statistical tool. The goals of the course are: understanding of the theory, its use in the analysis of real data, analysis of real data and interpretation of the results.

    Intended learning outcomes:
    Students acquire the knowledge for the independent work in the field of statistical modeling. This ability enables an upgrade to the different fields of scientific, research and expert work.



Main contact:
e-mail: info.stat (at)

Contact for administrative questions (enrolment, technical questions):
Katarina Erjavec Drešar
University of Ljubljana, Faculty of electrical engineering, Tržaška cesta 25, 1000 Ljubljana.
room num.: AN012C-ŠTU
phone: 01 4768 209
e-mail: katarina.erjavec-dresar (at)


Facebook stran 

The World of Statistics