Published

2026-01-01

Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers

Desempeño y concordancia entre algunas pruebas de normalidad en presencia y ausencia de valores atípicos

DOI:

https://doi.org/10.15446/rce.v49n1.118393

Keywords:

Concordance, Normality, Outliers, Performance, Simulation (en)
Concordancia, Desempeño, Pruebas de normalidad, Simulación, Valores atípicos (es)

Downloads

Authors

  • Jerfson Honório Universidade Federal de Pernambuco
  • Jorge A. Sousa Universidade Federal de Campina Grande image/svg+xml
  • Amanda S. Gomes Universidade Federal de Campina Grande image/svg+xml

This study evaluated the performance of various normality tests including Shapiro–Wilk, Shapiro–Francia, Anderson–Darling, Lilliefors, Cramer–von Mises, and Jarque–Bera under different conditions, both with and without the presence of outliers. Monte Carlo simulations were conducted to calculate the type I error rates, power, and the Kappa–Fleiss agreement coefficient, which measured the concordance among the tests. For normally distributed data without outliers, the Shapiro–Wilk and Shapiro–Francia tests showed the best control over the type I error rate. In contrast, with the introduction of outliers, the Lilliefors and Cramer–von Mises tests performed better. In terms of test power, the Shapiro–Wilk and Shapiro–Francia tests performed best for distributions without outliers, while the Jarque–Bera test was more robust in the presence of outliers. Overall, the results highlight the sensitivity of these tests to sample size and the presence of outliers, suggesting that Shapiro–Wilk and Shapiro–Francia are suitable for data without outliers, while Jarque–Bera may be preferred in contaminated samples. The tests showed higher concordance for exponential and lognormal distributions but lower concordance for beta, χ², and t-Student distributions, illustrating the complexity of normality identification across various contexts.

Este estudio evaluó el desempeño de diversas pruebas de normalidad incluyendo Shapiro–Wilk, Shapiro–Francia, Anderson–Darling, Lilliefors, Cramer–von Mises y Jarque–Bera bajo diferentes condiciones, tanto con como sin la presencia de valores atípicos. Se realizaron simulaciones de Monte Carlo para calcular las tasas de error tipo I, la potencia y el coeficiente de concordancia Kappa–Fleiss, que mide la concordancia entre las pruebas.

Para datos distribuidos normalmente sin valores atípicos, las pruebas de Shapiro–Wilk y Shapiro–Francia mostraron el mejor control sobre la tasa de error tipo I. En contraste, con la introducción de valores atípicos, las pruebas de Lilliefors y Cramer–von Mises tuvieron un mejor desempeño. En términos de potencia, las pruebas de Shapiro–Wilk y Shapiro–Francia obtuvieron los mejores resultados para distribuciones sin valores atípicos, mientras que la prueba de Jarque–Bera fue más robusta en presencia de valores atípicos.

En general, los resultados destacan la sensibilidad de estas pruebas al tamaño de la muestra y a la presencia de valores atípicos, sugiriendo que Shapiro–Wilk y Shapiro–Francia son adecuadas para datos sin valores atípicos, mientras que Jarque–Bera puede ser preferida en muestras contaminadas. Las pruebas mostraron mayor concordancia para distribuciones exponenciales y lognormales, pero menor concordancia para distribuciones beta, χ² y t-Student, lo que ilustra la complejidad de identificar la normalidad en diversos contextos.

References

Anderson, T. W. & Darling, D. A. (1952). Asymptotic theory of certain “goodness of fit” criteria based on stochastic processes. The Annals of Mathematical Statistics, 23(2), 193–212.

Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20, 37–46.

Cramer, H. (1957). Mathematical theory of statistics. The Annals of Mathematical Statistics.

Fleiss, J. L. (1971). Measuring nominal scale agreement among many raters. Psychological Bulletin, 76(5), 378–382.

Jarque, C. M. & Bera, A. K. (1980). Efficient tests for normality, homoscedasticity and serial independence of regression residuals. Economics Letters, 6, 255–259.

Lilliefors, H. W. (1967). On the Kolmogorov–Smirnov test for normality with mean and variance unknown. Journal of the American Statistical Association, 62(318), 399–402.

Morettin, P. A. & de O. Bussab, W. (2010). Estatística Básica (6ª ed.). Saraiva.

R Core Team (2024). R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria.

Shapiro, S. S. & Francia, R. S. (1972). An approximate analysis of variance test for normality. Journal of the American Statistical Association, 67(337), 215–216.

Shapiro, S. S. & Wilk, M. B. (1965). An analysis of variance test for normality (complete samples). Biometrika, 52(3/4), 591–611.

How to Cite

APA

Honório, J., A. Sousa, J. & S. Gomes, A. (2026). Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers. Revista Colombiana de Estadística, 49(1), 275–291. https://doi.org/10.15446/rce.v49n1.118393

ACM

[1]
Honório, J., A. Sousa, J. and S. Gomes, A. 2026. Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers. Revista Colombiana de Estadística. 49, 1 (Jan. 2026), 275–291. DOI:https://doi.org/10.15446/rce.v49n1.118393.

ACS

(1)
Honório, J.; A. Sousa, J.; S. Gomes, A. Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers. Rev. colomb. estad. 2026, 49, 275-291.

ABNT

HONÓRIO, J.; A. SOUSA, J.; S. GOMES, A. Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers. Revista Colombiana de Estadística, [S. l.], v. 49, n. 1, p. 275–291, 2026. DOI: 10.15446/rce.v49n1.118393. Disponível em: https://revistas.unal.edu.co/index.php/estad/article/view/118393. Acesso em: 9 feb. 2026.

Chicago

Honório, Jerfson, Jorge A. Sousa, and Amanda S. Gomes. 2026. “Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers”. Revista Colombiana De Estadística 49 (1):275-91. https://doi.org/10.15446/rce.v49n1.118393.

Harvard

Honório, J., A. Sousa, J. and S. Gomes, A. (2026) “Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers”, Revista Colombiana de Estadística, 49(1), pp. 275–291. doi: 10.15446/rce.v49n1.118393.

IEEE

[1]
J. Honório, J. A. Sousa, and A. S. Gomes, “Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers”, Rev. colomb. estad., vol. 49, no. 1, pp. 275–291, Jan. 2026.

MLA

Honório, J., J. A. Sousa, and A. S. Gomes. “Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers”. Revista Colombiana de Estadística, vol. 49, no. 1, Jan. 2026, pp. 275-91, doi:10.15446/rce.v49n1.118393.

Turabian

Honório, Jerfson, Jorge A. Sousa, and Amanda S. Gomes. “Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers”. Revista Colombiana de Estadística 49, no. 1 (January 30, 2026): 275–291. Accessed February 9, 2026. https://revistas.unal.edu.co/index.php/estad/article/view/118393.

Vancouver

1.
Honório J, A. Sousa J, S. Gomes A. Performance and Agreement Between Some Normality Tests Under the Presence and Lack of Outliers. Rev. colomb. estad. [Internet]. 2026 Jan. 30 [cited 2026 Feb. 9];49(1):275-91. Available from: https://revistas.unal.edu.co/index.php/estad/article/view/118393

Download Citation

CrossRef Cited-by

CrossRef citations0

Dimensions

PlumX

Article abstract page views

20

Downloads

Download data is not yet available.