GSMS Course Registration

Course information

Course: Generalized Linear and Mixed Effects Models - ONLINE

NB: In September 2020, this course will be given online. Consequences for and details of the exact implementation (content, time schedule, number of participants, EC’s, the option of taking an exam….) are therefore uncertain and might still change.

Using the linear model as a starting point, we extend the methodology of this model to situations with either non-normal responses (generalized linear models), clustered data (linear mixed effects models) or both (generalized linear mixed effects models), and hence learn to apply and understand mixed models for continuous, dichotomous and count outcome variables in relation to explanatory variables, for both cross-sectional and grouped/longitudinal data.

Organization and materials used
Within two weeks, five online lecture sessions of 2- 2.5 hours will be given. After each session, practical exercises (approximately 2 hours work from home) will be provided using SPSS (or R), as well as the worked-out answers. Feedback on these exercises will be offered online, as well as houd-outs of the lecture-slides. Additional reading material for R users is the book by Julian J. Faraway: Extending the linear model with R. Generalized Linear, Mixed Effects and Nonparametric Regression Models (2016, ISBN-13: 97-1-4987-2096-0).

Intended for
PhD students, and master students interested in statistical models for analysing data with cluster structures, for example in longitudinal or multilevel data, and/or non-normal response variables (dichotomous, counts). Students entering this course should have knowledge of and experience in using basic statistical concepts and techniques, including multiple linear regression analysis and analysis of variance. This basic knowledge is provided by the Basic Medical Statistics course.

The extended family of (generalized) linear mixed effects models is a useful statistical toolbox for the analysis of clustered data (e.g. members of the same family, patients within one hospital, repeated measures within individuals, etc.). This course will provide knowledge on the concepts and underlying theory of linear (mixed) models and generalized linear (mixed) models for cross-sectional, nested and longitudinal data and numerical or dichotomous outcome variables, enabling the course participants to recognize the need for these models. In this course we will learn how to build, examine, interpret, expand and compare these models using estimating equations (GEE) or (restricted) maximum likelihood estimation ((RE)ML), using practical examples throughout. In the accompanying exercises, the course participants will have the possibility of practising these skills themselves using SPSS (or R).                              

The main topics of the course will be:

·          Linear mixed models

·          Linear mixed effects models

·          Generalized linear models

·          Generalized linear mixed effects models (clustered data)

·          Model specification, diagnostics and selection approaches


For those who want to dive deeper into longitudinal data analysis, the course “Applied longitudinal data analysis” is recommended.

Basic Medical Statistics (or an equivalent course, see above)

Not compulsory. NB: date is still unsure, probably October 19 or later  

For participating in the course without exam at least 80% attendance is obligatory.

Schedule 2020

September 14, 15, 17, 21 and 22
Time: 10.00-12.30


September 14–22, 2020



EC (without exam)


EC (with exam)


Location address


Course coordinator

  • Sacha la Bastide, PhD



Target Groups

  • PhD students
  • ReMa students


fully booked

Deadline for registration

August 23, 2020


Register for the waiting list

Back to listing