Lesson 9: Poisson Regression

Printer-friendly versionPrinter-friendly version

Introduction to Poisson Regression

Poisson regression is also a type of GLM model where the random component is specified by the Poisson distribution of the response variable which is a count. When all explanatory variables are discrete, log-linear model is equivalent to poisson regression model. For more on Poisson regression models beyond to what is covered in this lesson, see Agresti (2007), Sec. 3.3,  and Agresti (2013), Section 4.3 (for counts), Section 9.2 (for rates), and Section 13.2 (for random effects).

Poisson distribution and Poisson sampling were introduced at the very beginning of the course. For example, the analysis of the World Cup Soccer data, where we estimated the mean number of goals per team, and expected probabilities of teams scoring a certain number of goals (or search this site for One-way Frequency Tables). 

Key Concepts:

  • Poisson Regression for Count data
  • Poisson Regression for Rate data

Objectives

  • Learn how to fit and evaluate a Poisson Regression model

Useful Links