We continue our study of methods for analyzing categorical data in this chapter. Inference in Chapter 8 focused on comparing proportions in one-sample and two-sample settings. We now study how to compare two or more populations when the response variable has two or more categories and how to test whether two categorical variables are independent. A single statistical test handles both settings.

The first section of this chapter gives the basics of statistical inference that are appropriate. A goodness-of-fit test is presented in the second section.

The methods detailed in this chapter will help answer questions such as

• Is there an association between whether a lost wallet will be returned and whether there is money in the wallet?
• Is the amount of fruit consumption related to the level of physical activity in college students?
• Is aggressive behavior in dementia patients more frequent when there is a full moon?