An Empirical Comparison of the Z-Variance and Box-Scheffé Tests for Homogeneity of Variance
- 1 December 1975
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 40 (4) , 519-524
- https://doi.org/10.1007/bf02291553
Abstract
This brief report provides a comparison of the Z-variance and Box-Scheffé tests for homogeneity of variance. Both procedures are relatively simple to perform and both may be readily utilized in complex, multifactor designs. The Z-variance test is not robust against non-normality; the Box-Scheffé test is robust against non-normality but is not nearly as powerful as the Z-variance test.Keywords
This publication has 6 references indexed in Scilit:
- A Simple Test for Heterogeneity of Variance in Complex Factorial DesignsPsychometrika, 1974
- Robust Large-Sample Tests for Homogeneity of VariancesJournal of the American Statistical Association, 1973
- Jackknifing VariancesThe Annals of Mathematical Statistics, 1968
- NON-NORMALITY AND TESTS ON VARIANCESBiometrika, 1953
- A GENERAL DISTRIBUTION THEORY FOR A CLASS OF LIKELIHOOD CRITERIABiometrika, 1949
- The Statistical Analysis of Variance-Heterogeneity and the Logarithmic TransformationJournal of the Royal Statistical Society Series B: Statistical Methodology, 1946