Which of the following is an assumption of the chi-square test?

• A. Frequencies are individual counts
• B. Data must be continuous
• C. There must be a linear relationship
• D. Data must be normally distributed

Answer: (A)

The chi-square test is built for categorical data expressed as counts in mutually exclusive categories. It works by comparing what you actually observe in each category with what would be expected if there were no association (or if the data followed a specified distribution). Because the data are frequencies, the essential requirement is that observations are counts, not continuous measurements. The test does not rely on normal distribution or a linear relationship, and it doesn’t require the data to be continuous. Instead, independence of observations and sufficiently large expected counts in each category are relied upon. So saying that data are individual counts captures the key assumption of the chi-square test.