Abstract
This paper deals with testing equality of variances of observations in the different treatment groups assuming treatment effects are fixed. We study the distribution of a test statistic which is known to perform comparably well with other statistics for the same purpose under normality. The statistic we consider is based on Shannon’s entropy for a distribution function. We will derive the asymptotic expansion for the distribution of the test statistic based on Shannon’s entropy under nonnormality and numerically examine its performance in comparison with the modified likelihood ratio criteria for normal and some nonnormal populations.
Similar content being viewed by others
References
Bartlett MS (1937) Properties of sufficiency and statistical tests. Proc R Soc Lond Ser A 160:268–282
Bhattacharya RN, Ghosh JK (1978) On validity of the formal Edgeworth expansion. Ann Stat 6:434–451
Boos DD, Brownie C (2004) Comparing variances and others measures of dispersion. Stat Sci 19:571–578
Box GEP (1953) Nonnormality and tests of variances. Biometrika 40:318–335
Browne MW (1984) Asymptotically distribution-free methods for the analysis of covariance structures. Br J Math Stat Psychol 37:62–83
Chao MT, Glaser RE (1978) The exact distribution of Bartlett’s test statistic for homogeniety of variances with unequal samples sizes. J Am Stat Assoc 73:422–426
Conover WJ, Johnson ME, Johnson MM (1981) A comparative study of test of homogeniety of variances: with applications to the outer continental shelf bindding data. Technometrics 23:351–361
Dudewicz EJ, van der Muelen EC (1981) Entropy based tests of uniformity. J Am Stat Assoc 76:967–974
Dyer DD, Keating JP (1980) On the determination of critical values for Bartlett’s test. J Am Stat Assoc 75:313–319
Fujikoshi Y, Ohmae M, Yanagihara H (1999) Asymptotic approximations of the null distribution of the one-way ANOVA test statistic under nonormality. J Japn Stat Soc 29:147–161
Glaser RE (1976) Exact critical values for Bartlett’s test for homogeneity of variances. J Am Stat Assoc 71:488–490
Hall P (1992) The bootstrap and Edgeworth expansions. Springer, New York
Harrar SW, Gupta AK (2006) Asymptotic expansion of the null distribution of F-statistic for one-way ANOVA under non-normality. Ann Inst Stat Math (in Press)
Kendall M, Stuart A, Ord JK (1987) Kendall’s advanced theory of statistics: distribution theory, 5th edn, vol 1. Oxford University Press, New York
Lehmann EL (1986) Testing statistical hypotheses. Springer, New York
Mardia KV (1970) Measures of multivariate skewness and kurtosis with applications. Biometrika 57: 519–530
Menéndez M, Morales D, Pardo L (1997) Maximum entropy principle and statistical inference on condensed ordered data. Stat Prob Lett 34:85–93
Nayak TK (1985) On diversity measures based on entropy functions. Commun Stat Theory Methods 14: 203–215
Nayak TK (1986) Sampling distributions in analysis of diversity. Sankhya Ser B 48:1–9
Neyman J, Pearson ES (1931) On the Problem of k-samples. Bull Acad Pol Sci Lett A, pp 460–481
Pardo L, Salicrú M, Menéndez ML, Morales D (1995) A test for homogeneity of variances based on Shannon’s entropy. Metron 53:135–146
Prescott P (1976) On a test for normality based on sample entropy. J R Stat Soc Ser B 38:254–256
Rao CR, Nayak TK (1985) Cross entropy, dissimilarity measures and characterization of quadratic entropy. IEEE Trans Info Theory 5:589–593
Shoemaker LH (2003) Fixing the F test for equal variances. Am Stat 57:105–114
Sugiura N, Nagao H (1969) On Bartlett’s test and Lehmann’s test for homogeneity of variances. Ann Math Stat 40:2018–2032
Tonda T, Wakaki H (2003) Asymptotic expansion of the null distribution of the likelihood ratio statistic for testing the equality of variances in a non-normal one-way ANOVA model. Hiroshima Math J 33:113–126
Vasicek O (1976) A test for normality based on sample entropy. J R Stat Soc Ser B 38:54–59
Yanagihara H (2000) Asymptotic expansion of the null distribution of the one-way ANOVA test statistic for heteroscedastic case under nonnormality. Commun Stat Theory Methods 29:463–476
Yanagihara H (2003) Asymptotic expansion of the null distribution of test statistic for linear hypothesis in non-normal linear model. J Multivariate Anal 84:222–246
Yanagihara H (2005) A family of estimators for multivariate kurtosis in a nonnormal linear regression model. J Multivariate Anal (in press)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Gupta, A.K., Harrar, S.W. & Pardo, L. On testing homogeneity of variances for nonnormal models using entropy. Stat. Meth. & Appl. 16, 245–261 (2007). https://doi.org/10.1007/s10260-007-0055-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10260-007-0055-7