Chapter 9 Poisson Regression

In Chapter 9 we will round out our discussion of the GLM with Poisson regression.

• Poisson regression can be a useful modeling approach for handling count dependent variables
  • Counts typically describe nonnegative (or only positive) integer.
  • Examples of counts are number of drinks per day, children per household, etc.
• In certain contexts, the Poisson distribution describes the number of events that occur in a given time period
  • \(\mu\) typically represents the mean number of events per period
  • In the Poisson distribution, the mean is also equal to the variance.
• One important consideration when fitting Poisson regression models is overdispersion
  • We will look at how one might assess overdispersion in Poisson regression and suggest some alternative procedures. A