ERIC Number: ED117150
Record Type: Non-Journal
Publication Date: 1975-Apr
Reference Count: N/A
Selection of Subsample Sizes for the Bartlett and Kendall Test of Homogeneity of Variance.
Martin, Charles G.; Games, Paul A.
Power and stability of Type I error rates are investigated for the Bartlett and Kendall test of homogeneity of variance with varying subsample sizes under conditions of normality and nonnormality. The test is shown to be robust to violations of the assumption of normality when sampling is from a leptokurtic population. Suggestions for selecting subsample sizes which will produce maximum power are given for small, intermediate and large sample situations. A formula for estimating power in the equal n case is shown to give results approximating empirical results. The problem of heterogeneous within cell variances and unequal n's is discussed. (Author)
Publication Type: Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A