Akademik Veri Yönetim Sistemi
Selçuk Journal Of Applied Mathematics, cilt.7, sa.7, ss.81-90, 2006 (Hakemli Dergi)
In the first part of this study, the results of heteroscedasticity in one way fixed effect ANOVA have been examined with a close concern on large sample approximations of treatment and error mean sum of squares and distortion of the distribution of the F ratio. Second part includes the presentation of new and simple approximation procedure which intends to create an easy and applicable alternative. The purpose of this new approximation procedure is to preserve the actual Type I error rate at a level determined by the researcher and to increase the power as well. Third part of the study consist of a simulation study which was implemented to compare the actual significance level and power of the new approximation, conventional F test and two other alternatives (Welch Test, Kruskal-Wallis Test). Finally, some recommendations about the preference of these tests for different types of experimental conditions were given.