Some Reasons for Not Using the Yates Continuity Correction on 2×2 Contingency Tables

Abstract In a contingency table with fixed marginal totals, and with row totals or column totals equal to each other, the Yates correction and the Kendall-Stuart correction for continuity improve estimates of the unknown probabilities. Otherwise only the Kendall-Stuart correction may be relied on to improve estimates over the chi-square approximation to the uncorrected statistic. If some marginal totals are random, the Yates corrected statistic provides a test different than the test which uses the uncorrected statistic.