Multi-level Modelling with R

Institution: see Organisers & Supporters

Programme of study: International Research Workshop

Lecturer: Dr. Daniel Lüdecke (UKE Hamburg)

Date: see Workshop Programme

Max. number of participants: 20

Credit Points: 5 CP for participating in the whole IRWS

Language of instruction: English

Contents:  The course teaches how to fit multilevel regression models with the statistical programming language R. First, simple (generalized) linear regression models are introduced to show important basic principles of modeling, like simple regression, interaction terms, non-linear relationships between predictors and outcome (polynomial and spline terms). Later, the application of these principles in a multilevel framework is demonstrated. Furthermore, graphical representation of complex mixed models is covered, which helps communicate complicated models even for a broad audience that is less familiar with such modeling techniques.

Successful participation requires basic knowledge of regression modeling techniques. Students are encouraged to bring their own laptops with the free software R ( and RStudio ( installed. All source code to run the examples is provided in preparation for the course.

Requirements: Knowledge of classic regression modeling (familiarity with terms like dependent and independent variables, linear and logistic regression, estimate, …)

Recommended readings:

  • Harrison, X. A., Donaldson, L., Correa-Cano, M. E., Evans, J., Fisher, D. N., Goodwin, C. E. D., … Inger, R. (2018). A brief introduction to mixed-effects modelling and multi-model inference in ecology. PeerJ, 6, e4794.
  • Bolker, B. M., Brooks, M. E., Clark, C. J., Geange, S. W., Poulsen, J. R., Stevens, M. H. H., & White, J.-S. S. (2009). Generalized linear mixed models: a practical guide for ecology and evolution. Trends in Ecology & Evolution, 24(3), 127–135.

Required R packages:

  • Modelling: lme4, glmmTMB, GLMMadaptive
  • Visualization: ggeffects, sjPlot, see
  • Summaries and Statistics: parameters, effectsize
  • Model Quality: performance
  • Data preparation: sjmisc, dplyr, tidyr

The easiest way to install the relevant core packages is by running the following code:

install.packages("easystats", repos = "")

To install further required packages, run:

install.packages(c("lme4", "glmmTMB", "effects", "emmeans", "modelsummary",
"sjmisc", "sjlabelled", "ggeffects", "sjPlot", "dplyr", "tidyr"),
dependencies = TRUE)

You must register for the International Research Workshop to participate in this course.