The use of Kramer's proposed approximate method for multiple-range tests with unequal sample sizes may result in lower power for these tests than for the Tukey A test, a reversal of the situation for equal-sized samples. A modification of Kramer's procedure proposed by Duncan results in multiple-range tests which are more powerful than the Tukey A test.
Get full access to this article
View all access options for this article.
References
1.
DuncanD. B.Multiple range tests for correlated and heteroscedastic means. Biometrics, 1957, 13, 164–176.
2.
KramerC. Y.Extension of multiple range tests to group means with unequal numbers of replications. Biometrics, 1956, 12, 307–310.
3.
SmithR. A.The effect of unequal group size on Tukey's HSD procedure. Psychometrika, 1971, 36, 31–34.
