Which data scenario is appropriate for a chi-square test?

• A. One continuous dependent variable
• B. Two categorical variables
• C. Paired samples
• D. Nonlinear relationships

Answer: (B)

Chi-square tests are used with categorical data to see if observed counts in categories differ from what would be expected if there were no association between variables. When you have two categorical variables, you can tabulate the counts for each combination of categories in a contingency table and test whether the variables are independent. This makes the scenario with two categorical variables exactly suited for a chi-square test of independence.

Keep in mind that chi-square relies on counts in categories and assumes that observations are independent and that expected counts in each cell are large enough (typically at least 5). This is why the other scenarios don’t fit as well: a single continuous variable calls for tests like t-tests or ANOVA, paired samples involve related observations (for which McNemar’s test or other methods are used rather than the standard chi-square), and nonlinear relationships are explored with correlation or regression methods rather than chi-square.