Cochran’s Q test indicates whether the distribution of binary values appears to differ across three or more columns when the values in a particular row are related. For example, it can be used to assess whether voting patterns significantly differ in three or more elections, where each row represents an individual voter, and each cell takes one of two possible values. Cochran’s Q test is the multi-column equivalent of a McNemar test.

To perform Cochran’s Q test on three or more category columns:

- In the Summary view, use the confidence slider to choose a desired confidence level
- Command-click three or more category columns of interest on the left
- Check the box labeled
*Repeated measures*below the summary picture - The result of Cochran’s Q test will appear in the Bottom Line

Note that the test will only be performed if the selected columns take on the same set of (two) values, and have the same category labels, if any.

See also:

- Performing a McNemar test for the marginal homogeneity of two category columns that are matched or related
- Performing a chi-square test of a category column’s independence from another category column
- Performing a chi-square test of two or more category columns’ distributions
- Assigning labels to the values of a category column
- Formatting descriptive and inferential statistics
- About the Summary view