What is Generalized Linear Models?

Generalized Linear Models (GLMs) are a flexible generalization of ordinary linear regression that allows for response variables that have error distribution models other than a normal distribution. GLMs extend the linear model in two ways: by allowing the mean of the response variable to be related to the linear predictor via a link function and by allowing the variance of each observation to be a function of its predicted value. They are commonly used for regression analysis where the response variable is not normally distributed, such as in binary classification (logistic regression), count data (Poisson regression), and survival analysis.