Count Regression Models

Like continuous variables, count variable are numerical.  So it seems you should be able to apply methods for continuous data to count data.

After all, a mean makes sense for both.

But there are differences in the types of distributions that count and continuous variables tend to follow, and these differences can actually make the results quite different.

It’s generally a better idea to apply models that assume count data.  Get more info on these kinds of models here.

The Craft of Statistical Analysis Free Webinar

Poisson and Negative Binomial Regression for Count Data

Related Statistical Speaking Membership Webinars

• Zero Inflated Models

• Making Sense of Statistical Distributions

Articles About Count Data and the Poisson Family of Regression Models

• Poisson Regression Analysis for Count Data

• Differences Between the Normal and Poisson Distributions

• Poisson and Negative Binomial Regression for Count Data

• Analyzing Zero-Truncated Count Data: Length of Stay in the ICU for Flu Victims

• Two-Way Tables and Count Models: Expected and Predicted Counts

• Understanding Incidence Rate Ratios through the Eyes of a Two-Way Table

• The Exposure Variable in Poisson Regression Models

• Zero-Inflated Poisson Models for Count Outcomes

• When Can Count Data be Considered Continuous?

• Interpreting Regression Coefficients in Models other than Ordinary Linear Regression

• Count Models: Understanding the Log Link Function

• Issues with Truncated Data

• Overdispersion in Count Models: Fit the Model to the Data, Don’t Fit the Data to the Model

Articles About Count Models in the Context of Generalized Linear Models

• Confusing Statistical Term #7: GLM

• Generalized Linear Models in R, Part 6: Poisson Regression for Count Variables

• Generalized Linear Models in R, Part 7: Checking for Overdispersion in Count Regression

• Five Extensions of the General Linear Model

• How to Combine Complicated Models with Tricky Effects

• When Dependent Variables Are Not Fit for Linear Models, Now What?

• 6 Types of Dependent Variables that will Never Meet the GLM Normality Assumption

• What Happened to R squared?: Assessing Model Fit for Logistic, Multilevel, and Other Models that use Maximum Likelihood Webinar

• Interpreting Regression Coefficients in Models other than Ordinary Linear Regression