Abstract
Paired rankings arise when each subject in a study independently ranks a set of items, undergoes a treatment, and afterwards ranks the same set of items. For such data, a statistical test is proposed to detect if the subjects’ posttreatment rankings have moved systematically toward some unknown ranking or set of rankings. The null hypothesis for this test is that each subject’s post-treatment ranking is symmetrically distributed about his pretreatment ranking. The exact and asymptotic null distributions of the test statistic are simulated and compared, and the power of the test is studied. Using paired rankings from an experimental course in literary criticism, we also offer some graphical methods for representing such data that help us to interpret the test results.