Skip to content

Applied Generalized Linear Mixed Models with R


Course title

Applied Generalized Linear Mixed Models with R.



Tim Robinson. Dept. of Statistics, Univ. Wyoming. 

Tim Robinson is a professor at the Statistics Dept. University of Wyoming. He got his B.S. in mathematics and Psychology from James Madison University in 1989 and his M.a. and PhD Degrees in Statistics from the Virginia Polytechnic Institute in 1994 and 1997 respectively. Main research interests: Design of Experiments, Response Surface methodology, Categorical Data Analysis and applications in engineering, medicine and the environment.


Course language



Course schedule

June 19 to 23, from 10:00am to 1:00pm.



This course provides an introduction to generalized linear mixed models (GLMM) using R. Generalized linear mixed models have become standard fare for analyzing clustered/correlated data from exponential family member probability distributions (presence/absence data, count data, exponential data and normal data). The course emphasizes the applications of these models but when necessary, an intuitive theoretical framework is developed. 



  1. Identify situations in which linear models, linear mixed models, generalized linear models and generalized linear mixed models are appropriate for modeling.
  2. Understand the difference between fixed and random effects.
  3. Create a model matrix based upon the data collection protocol.
  4. Understand the difference between subject-specific and population-averaged effects in a mixed model.
  5. Run a Bayesian analysis to estimate parameters in a mixed model and subsequently interpret Bayesian predictions.
  6. Perform basic power analyses to evaluate competing sampling plans for hierarchical data.
  7. Utilize R for running linear models, linear mixed models, generalized linear models and generalized linear mixed models.


Lecture plan

  1. Multiple Linear Regression
  2. Linear models with clustered data (Linear Mixed Modeling)
    1. Random intercepts
    2. Random coefficient models
    3. Diagnostics
  3. Generalized Linear Mixed Models
    1. Poisson models for count data
    2. Gamma models
    3. Logit models for presence/absence data
  4. The utility of Bayesian approaches to the GLMM
  5. Power analyses for detecting trends mixed logit models



Students will be expected to complete course exercises using example data sets upon course completion.