The purchasing manager for a chain of grocery stores is interested in customer's preference for non-alcoholic beverages. She wondered if there was a relationship between the customer's beverage preference and the customer's income class. She randomly sampled 500 customers and asked their non-alcoholic beverage preference (soft drinks, energy drinks, fruit juices, vitamin water, or other) and what their income class is (lower class, lower middle class, middle class, upper middle class, upper class). Assuming all conditions are satisfied, which of the following tests should the manager use to test her hypothesis?
A. The chi-square test of homogeneity.
B. The goodness-of-fit chi-square test.
C. The chi-square test of independence.
D. The two-sample z-test for proportions.

The chi-square test of independence is used to determined whether there is a relationship between two categorical variable which in this study is to establish if there is a relationship between a customer's beverage preference and his/her income class (these are categorical variables).

The null hypothesis would be that no relationship exists between the variables while the alternative would be that there is a relationship between the two variables.