ABSTRACT
When observing two variables X and Y , often the question arises whether or
not X and Y are independent. For example, is gender associated with voting
behavior? In order to tackle such a question, the data can be summarized
within a contingency table. If X and/or Y are continuous, one must create
categories. Then, Pearson’s χ2 test, already introduced for a 2xk table in
Chapter 5, can be applied. The null hypothesis states that the two variables
X and Y are independent. Under the alternative, there is an association.
