an extension of Tukey’s honestly significant difference test (HSD test) so that it can be used with samples of unequal size. Whereas the HSD test yields a single critical difference (CD) for each pair of means, the Tukey–Kramer test uses a different CD as required to evaluate the significance of the difference between each pair of means. [John Wilder Tukey (1915–2000) and Clyde Y. Kramer, U.S. statisticians]