Efficiency Evaluation of Statistical Tests for Homogeneity of Variances under Normal, Beta, and Weibull Distributional Frameworks

Article Sidebar

PDF
DOI: https://doi.org/10.28924/2291-8639-23-2025-240
Published: Oct 8, 2025
Cite as:
Saowapa Chapitak, Jarukit Jaipetch, Kunita Wichayacheewin, Wasutida Suwanrach, Boonyarit Choopradit, Efficiency Evaluation of Statistical Tests for Homogeneity of Variances under Normal, Beta, and Weibull Distributional Frameworks, Int. J. Anal. Appl., 23 (2025), 240.

Main Article Content

Saowapa Chapitak, Jarukit Jaipetch, Kunita Wichayacheewin, Wasutida Suwanrach, Boonyarit Choopradit

Abstract

This research endeavor aims to evaluate six test statistics relevant to assessing of homogeneity of variance (HOV): Bartlett’s (BL), Levene’s (LV), modified Levene’s (LVM), Klotz’s (KL), Layard’s (LY), and Samiuddin’s (SMD). Simulated datasets were generated under the frameworks of normal, Beta, and Weibull distributions, encompassing both three and four groups, while incorporating variations in sample sizes that were both equal and unequal. Each experimental condition was replicated 5,000 times to ensure the precision of statistical outcomes. In the context of the normal distribution, the BL, LY, and SMD statistics exhibited strong control over Type I error rates, with the BL and LY statistics achieving the highest statistical power among the tests classified as acceptable. Whereas the LV and LVM statistics demonstrated competence in error control, they were characterized by reduced power; conversely, the SMD statistic exhibited significantly low power. In contrast, the KL statistic consistently yielded inflated error rates, rendering it inappropriate for practical application. In the realm of the Beta distribution, the KL, LVM, and LY statistics emerged as the most proficient performers, adeptly preserving Type I error rates. The KL statistic, notwithstanding its mediocre performance under normal distribution conditions, demonstrated the greatest resilience within this specific context. The LVM statistic maintained a conservative approach; the LY statistic exhibited precision yet was somewhat less robust when faced with skewed data, the LV statistic demonstrated moderate effectiveness, the BL statistic was excessively cautious, and the SMD statistic was classified as unreliable. In relation to the Weibull distribution, the LY, SMD, KL, and LVM statistics consistently controlled the Type I error rates. The BL statistic performed satisfactorily but exhibited a slight inclination towards inflation of Type I error rates, whereas the LV statistic was assessed as unreliable. The BL statistic attained the highest statistical power, albeit with correspondingly elevated Type I error rates. The LVM and LY statistics demonstrated considerable power across diverse scenarios, with the LY statistic being preferentially utilized for small to medium sample sizes and the LVM statistic for larger sample sizes. The SMD and KL statistics consistently ranked lowest in terms of empirical power.

Article Details

References

  1. R.W. Johnson, Alternate Forms of the One-Way ANOVA F and Kruskal–Wallis Test Statistics, J. Stat. Data Sci. Educ. 30 (2022), 82-85. https://doi.org/10.1080/26939169.2021.2025177.
  2. B.L. Welch, On the Comparison of Several Mean Values: An Alternative Approach, Biometrika 38 (1951), 330-336. https://doi.org/10.1093/biomet/38.3-4.330.
  3. W.H. Kruskal, W.A. Wallis, Use of Ranks in One-Criterion Variance Analysis, J. Am. Stat. Assoc. 47 (1952), 583-621. https://doi.org/10.1080/01621459.1952.10483441.
  4. H. Scheffé, The Analysis of Variance, John Wiley & Sons, New York, 1959.
  5. H. Levene, Robust Tests for Equality of Variance, in: Contributions to Probability and Statistics: Essays in Honor of Harold Hotelling, Stanford University Press, California, pp. 278–292, 1960.
  6. G. W. Snedecor, W. G. Cochran, Statistical Methods, 8th ed. Iowa State University Press, 1989.
  7. M.B. Brown, A.B. Forsythe, Robust Tests for the Equality of Variances, J. Am. Stat. Assoc. 69 (1974), 364-367. https://doi.org/10.2307/2285659.
  8. H. B. Lee, G. S. Katz, A. F. Restori, A Monte Carlo Study of Seven Homogeneity of Variance Tests, J. Math. Stat. 6 (2010), 359-366. http://doi.org/10.3844/jmssp.2010.359.366.
  9. D. Sharma, B.M.G. Kibria, On Some Test Statistics for Testing Homogeneity of Variances: A Comparative Study, J. Stat. Comput. Simul. 83 (2013), 1944-1963. https://doi.org/10.1080/00949655.2012.675336.
  10. Y. Wang, P. Rodríguez de Gil, Y. Chen, J.D. Kromrey, E.S. Kim, et al., Comparing the Performance of Approaches for Testing the Homogeneity of Variance Assumption in One-Factor ANOVA Models, Educ. Psychol. Meas. 77 (2016), 305-329. https://doi.org/10.1177/0013164416645162.
  11. W.J. Conover, A.J. Guerrero-Serrano, V.G. Tercero-Gómez, An Update on ‘A Comparative Study of Tests for Homogeneity of Variance’, J. Stat. Comput. Simul. 88 (2018), 1454-1469. https://doi.org/10.1080/00949655.2018.1438437.
  12. W. Riansut, A Comparison of the Efficiency of the Test Statistics for Testing Homogeneity of Variance, Naresuan Univ. J. Sci. Technol. 26 (2018), 170-180.
  13. S. Sinsomboonthong, An Efficiency Comparison of 3 Groups Homogeneity of Population Variance Tests under Highly Kurtosis and Skewness Distributions, Thai Sci. Tech. J. 26 (2018), 721–738.
  14. K. Soikliew, A. Araveeporn, Modifications of Levene’s and O’Brien’s Tests for Testing the Homogeneity of Variance Based on Median and Trimmed Mean, Thai. Stat. 16 (2018), 106–128.
  15. K. Jiamwattanapong, N. Ingadapa, Performance of Tests for Homogeneity of Variances for More than Two Samples, Int. J. Manag. Appl. Sci. 6 (2020), 57-62.
  16. K. Sritan, B. Phuenaree, A Comparison of Efficiency for Homogeneity of Variance Tests under Log-normal Distribution, Asian J. Appl. Sci. 9 (2021), 254-259. http://doi.org/10.24203/ajas.v9i4.6692.
  17. Y. Zhou, Y. Zhu, W.K. Wong, Statistical Tests for Homogeneity of Variance for Clinical Trials and Recommendations, Contemp. Clin. Trials Commun. 33 (2023), 101119. https://doi.org/10.1016/j.conctc.2023.101119.
  18. M. S. Bartlett, Properties of Sufficiency and Statistical Tests, Proc. R. Soc. Lond. A 160 (1937), 268–282. https://doi.org/10.1098/rspa.1937.0109.
  19. J.L. Gastwirth, Y.R. Gel, W. Miao, The Impact of Levene’s Test of Equality of Variances on Statistical Theory and Practice, Stat. Sci. 24 (2009), 343-360. https://doi.org/10.1214/09-sts301.
  20. J. Klotz, Nonparametric Tests for Scale, Ann. Math. Stat. 33 (1962), 498-512. https://doi.org/10.1214/aoms/1177704576.
  21. F. Karaman, Generalization of Klotz’s Test, J. Appl. Sci. 9 (2009), 2916-2924. https://doi.org/10.3923/jas.2009.2916.2924.
  22. SAS Institute Inc, SAS/STAT ® 13.1 User’s Guide: The NPAR1WAY Procedure, Accessed: Feb. 11, 2025. https://support.sas.com/documentation/onlinedoc/stat/131/npar1way.pdf.
  23. M.W.J. Layard, Robust Large-Sample Tests for Homogeneity of Variances, J. Am. Stat. Assoc. 68 (1973), 195-198. https://doi.org/10.2307/2284168.
  24. M. Samiuddin, Bayesian Test of Homogeneity of Variance, J. Am. Stat. Assoc. 71 (1976), 515-517. https://doi.org/10.2307/2285344.
  25. S. Chaipitak, B. Choopradit, A New Test for Equality of Two Covariance Matrices in High-Dimensional Data, Math. Stat. 12 (2024), 455-464. https://doi.org/10.13189/ms.2024.120507.
  26. P.A. Games, H.B. Winkler, D.A. Probert, Robust Tests for Homogeneity of Variance, Educ. Psychol. Meas. 32 (1972), 887-909. https://doi.org/10.1177/001316447203200404.
  27. J.V. Bradley, Robustness?, Br. J. Math. Stat. Psychol. 31 (1978), 144-152. https://doi.org/10.1111/j.2044-8317.1978.tb00581.x.
  28. W.G. Cochran, The $chi^2$ Test of Goodness of Fit, Ann. Math. Stat. 23 (1952), 315-345. https://doi.org/10.1214/aoms/1177729380.
  29. B. Choopradit, S. Wasinrat, Zero-one Inflated Bell Distribution and Its Application to Insurance Data, Int. J. Math. Comput. Sci. (2025), 625-635. https://doi.org/10.69793/ijmcs/02.2025/sirithip.