Answers are grounded in this paper and cite their sources.
This research proposes a statistical test that accounts for changes in binary outcomes over time—an exact repeated measures test for binary observations. The test is particularly well suited to settings in which the objective is to assess the temporal effect of a factor, such as a treatment, advertising, or a political campaign. The proposed test is not time-symmetric: interchanging the vectors of initial and final values may lead to different test results. The test follows the Barnard test approach in computing the p -values.
No takes yet. Share an insight, caveat, or question.
P. S. Ruzankin (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: