A COMPARATIVE ANALYSIS OF BAYESIAN AND FREQUENTIST METHODS FOR INDEPENDENT K-SAMPLE TESTING

Pardomuan Robinson Sihombing

Abstract


Regional socioeconomic inequality remains a critical development challenge in Indonesia, with significant variations observed in Sumatra, Java-Bali, and other regions. This study conducted a comprehensive methodological comparison between Bayesian and frequentist approaches to test the average differences among three independent regional groups using five economic and social indicators from 2024-2025: Human Development Index (HDI), Gini ratio, poverty rate, unemployment rate, and economic growth. The authors evaluated Bayesian ANOVA against parametric ANOVA F and four nonparametric alternatives, including the Kruskal-Wallis test, permutation test, and median test, by assessing its performance under different assumption violations. Statistical analysis showed that HDI and Gini ratios showed significant regional differences across all methods, while poverty rates showed method-dependent outcomes, and unemployment and economic growth showed no significant regional differences. These findings demonstrate the importance of method selection based on assumption testing and highlight the advantages of the Bayesian approach for regional analysis with small samples. Policymakers should prioritize targeted interventions for disadvantaged regions while addressing income inequality in more developed regions.

Full Text:

PDF

References


H. Hill, B. P. Resosudarmo, and Y. Vidyattama, “Indonesia’s changing economic geography,” Bull. Indones. Econ. Stud., vol. 44, no. 3, pp. 407–435, 2008, doi: 10.1080/00074910802395344.

Badan Pusat Statistik, “Indonesia’s human development index (HDI) in 2025 reached 75.90.” 2025. [Online]. Available: https://www.bps.go.id/en/pressrelease/2025/11/05/2480

Badan Pusat Statistik, Statistical Yearbook of Indonesia 2025. Jakarta: BPS-Statistics Indonesia, 2025.

D. C. Montgomery, Design and analysis of experiments, 10th ed. Hoboken: Wiley, 2020.

M. W. Fagerland and L. Sandvik, “Performance of five two-sample location tests for skewed distributions with unequal variances,” Contemp. Clin. Trials, vol. 30, no. 5, pp. 490–496, 2009, doi: 10.1016/j.cct.2009.06.007.

W. H. Kruskal and W. A. Wallis, “Use of ranks in one-criterion variance analysis,” J. Am. Stat. Assoc., vol. 47, no. 260, pp. 583–621, 1952, doi: 10.1080/01621459.1952.10483441.

M. D. Ernst, “Permutation methods: A basis for exact inference,” Stat. Sci., vol. 19, no. 4, pp. 676–685, 2004, doi: 10.1214/088342304000000396.

A. M. Mood, “On the asymptotic efficiency of certain nonparametric two-sample tests,” Ann. Math. Stat., vol. 25, no. 3, pp. 514–522, 1954, doi: 10.1214/aoms/1177728719.

J. N. Rouder, R. D. Morey, P. L. Speckman, and J. M. Province, “Default Bayes factors for ANOVA designs,” J. Math. Psychol., vol. 56, no. 5, pp. 356–374, 2012, doi: 10.1016/j.jmp.2012.08.001.

J. van Doorn et al., “The JASP guidelines for conducting and reporting a Bayesian analysis,” Psychon. Bull. & Rev., vol. 28, no. 3, pp. 813–826, 2021, doi: 10.3758/s13423-020-01798-5.

E.-J. Wagenmakers et al., “Bayesian inference for psychology. Part I: Theoretical advantages and practical ramifications,” Psychon. Bull. & Rev., vol. 25, no. 1, pp. 35–57, 2018, doi: 10.3758/s13423-017-1343-3.

M. I. Pongge, E. M. Lawalu, M. Masri, and M. P. J. Gamatara, “Foreign investment, human development, and regional inequality in Indonesiah,” J. Econ. Res. Soc. Sci., vol. 9, no. 2, 2025, doi: ttps://doi.org/10.18196/jerss.v9i2.27522.

CELIOS, “Indonesia Inequality Report 2024.” Center for Equality and Livelihood Studies, 2024. [Online]. Available: https://celios.co.id/wp-content/uploads/2024/09/Indonesia_Inequality_Report_2024_EN.pdf

V. den Bergh et al., “A tutorial on conducting and interpreting a Bayesian ANOVA in JASP,” Annee. Psychol., vol. 121, no. 1, pp. 73–96, 2021, doi: 10.3917/anpsy1.201.0073.

E. Barzizza, N. Biasetton, and R. Ceccato, “Multi-aspect permutation tests for model selection,” Expert Syst. Appl., vol. 238, p. 121764, 2023, doi: 10.1111/exsy.13492.

D. W. Zimmerman, “A comparative study of the efficiency of the Wilcoxon test, Student’s t test, and the alternatives to Student’s t test,” Percept. Mot. Skills, vol. 114, no. 3, pp. 700–716, 2012.

S. S. Shapiro and M. B. Wilk, “An analysis of variance test for normality (complete samples),” Biometrika, vol. 52, no. 3--4, pp. 591–611, 1965, doi: 10.1093/biomet/52.3-4.591.

N. M. Razali and Y. B. Wah, “Power comparisons of Shapiro-Wilk, Kolmogorov-Smirnov, Lilliefors and Anderson-Darling tests,” J. Stat. Model. Anal., 2011.

D. W. Zimmerman, “A note on preliminary tests of equality of variances,” Br. J. Math. Stat. Psychol., vol. 57, no. 1, pp. 173–181, 2004, doi: 10.1348/000711004849222.

L. M. Lix, H. J. Keselman, and J. C. Keselman, “Consequences of assumption violations revisited: A quantitative review of alternatives to the one-way analysis of variance F test,” Rev. Educ. Res., vol. 66, no. 4, pp. 579–619, 1996, doi: 10.3102/00346543066004579.

R. A. Fisher, Statistical methods for research workers. Oliver and Boyd, 1925.

B. . Welch, “The Generalization of `Student’s’ Problem when Several Different Population Variances are Involved,” Biometrika, vol. 34, no. 1/2, pp. 28–35, 1947.

P. Good, Permutation tests: A practical guide to resampling methods for testing hypotheses, 2nd ed., vol. 2. New York: Springer, 2000.

K. J. Berry, J. E. Johnston, and P. W. Mielke, “Permutation methods,” Wiley Interdiscip. Rev. Comput. Stat., vol. 3, no. 6, pp. 527–542, 2011, doi: https://doi.org/10.1002/wics.177.

S. Siegel, Statistik Nonparametrik untuk Ilmu-ilmu Sosial. Jakarta: PT Gramedia Pustaka, 1997.

J. W. Tukey, “Comparing individual means in the analysis of variance.,” Biometrics, vol. 5, no. 2, pp. 99–114, 1949, doi: https://doi.org/10.2307/3001913.

O. J. Dunn, “Multiple comparisons using rank sums,” Technometricss, vol. 6, no. 3, pp. 241–252, 1964, doi: https://doi.org/10.1080/00401706.1964.10490181.

P. H. Westfall, W. O. Johnson, and J. M. Utts, “A Bayesian perspective on the Bonferroni adjustment,” Biometrika, vol. 84, no. 2, pp. 419–427, 1997, doi: https://doi.org/10.1093/biomet/84.2.419.

J. Cohen, Statistical power analysis for the behavioral sciences, 2nd ed. Lawrence Erlbaum Associates., 1988.

M. Tomczak and E. Tomczak, “The need to report effect size estimates revisited. An overview of some recommended measures of effect size,” Trends Sport Sci., vol. 1, no. 21, pp. 19–25, 2014.




DOI: https://doi.org/10.20527/ragam.v5i2.19876

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

RAGAM: Journal of Statistics and Its Application 

Program Studi Statistika, Fakultas MIPA, Universitas Lambung Mangkurat
Jalan A. Yani Km.36, Kampus ULM Banjarbaru, Kalimantan Selatan, Indonesia 70714

e-mail: [email protected]
website: https://ppjp.ulm.ac.id/journals/index.php/ragam

 

Lisensi Creative Commons


RAGAM: Journal of Statistics and Its Application is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.