Generalized Linear Models (GLM’s) are a parametric regression framework that encompasses many types of regressions: Linear Regression, Logistic Regression, Poisson Regression, Gamma Regression, etc. The main differences, as explained in the 1st intro video, is summarized by the following table:

We see the main differences in points 2-4: in GLM’s we are not limited to the normal distribution response but to other distributions that are part of the exponential family (Bernoulli/Binomial, Poisson, etc.); the connection between the mean and the linear predictor can be through some link-function; and the fitting procedure for the beta coefficients is done solely through maximum likelihood.

In this course we will learn how the GLM framework works and how to use it in R.

### Requirements

- Linear Algebra
- Calculus
- Intro to Probability
- Intro to Statistics
- Linear Models (Linear Regression)
- R Programming Language