15 Generalized linear model


So far our regression models all had a metric dependent variable. In this chapter we are going to look at the basic architecture of generalized linear models (GLM), a class of regression models that allow for different types of dependent variables, like binary, nominal, ordinal or count data. The focus of this chapter is on the main idea of the generalization, and to showcase the GLM family with one concrete example, namely logistic regression, which is used for a binary dependent variable.

The learning goals for this chapter are:

  • understand how to generalize linear regression modeling to other kinds of dependent variables
  • be able to run and interpret a logistic regression model with brms