Key points are not available for this paper at this time.
Three different methods for testing all pairs of yȳ k , - yȳ k’ were contrasted under varying sample size (n) and variance conditions. With unequal n’s of six and up, only the Behrens-Fisher statistic provided satisfactory control of both the familywise rate of Type I errors and Type I error rate on each contrast. Satisfactory control with unequal n’s of three and up is dubious even with this statistic.
Games et al. (1976) studied this question.