Comparison of the Statistical Power of Siegel-Tukey and Savage Tests: A Study with Monte Carlo Simulation

This study presents the results of a Monte Carlo simulation to compare the statistical power of Siegel-Tukey and Savage tests. The main purpose of the study is to evaluate the statistical power of both tests in scenarios involving Normal, Platykurtic and Skewed distributions over different sample sizes and standard deviation values.In the study, standard deviation ratios were set as 2, 3, 4, 1/2, 1/3 and 1/4 and power comparisons were made between small and large sample sizes. For equal sample sizes, small sample sizes of 5, 8, 10, 12, 16 and 20 and large sample sizes of 25, 50, 75 and 100 were used. For different sample sizes, the combinations of (4, 16), (8, 16), (10, 20), (16, 4), (16, 8) and (20, 10) small sample sizes and (10, 30), (30, 10), (50, 75), (50, 100), (75, 50), (75, 100), (100, 50) and (100, 75) large sample sizes were examined in detail.According to the findings, the power analysis under variance heterogeneity conditions shows that the Siegel-Tukey test has a higher statistical power than the other nonparametric Savage test at small and large sample sizes. In particular, the Siegel-Tukey test was reported to offer higher precision and power under variance heterogeneity, regardless of having equal or different sample sizes.

Algina, J., Olejnik, S., & Ocanto, R. (1989). Type I error rates and power estimates for selected two-sample tests of scale. Journal of Educational Statistics, 14(4), 373-384.

Arboretti, R., Fontana, R., Pesarin, F., & Salmaso, L. (2018). Nonparametric combination tests for comparing two survival curves with informative and non-informative censoring. Statistical Methods in Medical Research, 27(12), 3739-3769.

Chen, N., Valdes, D., Marlin, C., Blanchoud, H., Guerin, R., Rouelle, M., & Ribstein, P. (2019). Water, nitrate and atrazine transfer through the unsaturated zone of the Chalk aquifer in northern France. Science of the Total Environment, 652, 927-938.

Clifford B. R., & Thompson, G. L. (1992). A distribution-free rank-like test for scale with unequal population locations. Communications in Statistics-Simulation and Computation, 21(2), 353-371.

Fahoome, G., & Sawilowsky, S. S. (2000). Review of Twenty Nonparametric Statistics and Their Large Sample Approximations.

Feinberg, R. A., & Rubright, J. D. (2016). Conducting simulation studies in psychometrics. Educational Measurement: Issues and Practice, 35(2), 36-49.

Fleishman, A. I. (1978). A method for simulating non-normal distributions. Psychometrika, 43(4), 521-532.

Funato, M., Murakami, H., Kössler, W., & Mukherjee, A. (2024). Nonparametric tests for combined location-scale and Lehmann alternatives using adaptive approach and max-type metric. Journal of the Korean Statistical Society, 1-38.

Genz, A. S., Fletcher, C. H., Dunn, R. A., Frazer, L. N., & Rooney, J. J. (2007). The predictive accuracy of shoreline change rate methods and alongshore beach variation on Maui, Hawaii. Journal of Coastal Research, 23(1), 87-105.

Gibbons, J. D. (1993). Nonparametric Statistics: An Introduction (No. 90). Sage.

Lee, C. H. (2007). A Monte Carlo study of two nonparametric statistics with comparisons of type I error rates and power. Oklahoma State University.

Miramontes B. S., & Medina E. R. J. (2014). Análisis de la evolución temporal dela actividad vegetal en áreas de manglar (1990-2010): deltas de los ríos Yaqui y Mayo en Sonora, yrío Fuerte en Sinaloa, México. Licenciatura en Geoinformática.

Pawar, S. D., & Shirke, D. T. (2019). Nonparametric tests for multivariate multi-sample locations based on data depth. Journal of Statistical Computation and Simulation, 89(9), 1574-1591.

Ramazanov, S., & Senger, Ö. (2023). For small, equal and large sample sizes, Wald- Type I error rates of Wolfowitz, Kolmogorov-Smirnov and Mann-Whitney tests comparison. Journal of Ardahan University Faculty of Economics and Administrative Sciences, 5(2), 137-144.

Randles, R. H. & Wolfe, D. A. (1979). Introduction to the Theory of Nonparametric Statistics. John W iley & Sons, New York.

Savage, I. R. (1978). Nonparametric statistics: The field. In International Encyclopedia of Statistics, Vol. 1, ed. V. V. H. Kruskal and J. M. Tanur. New York: The Free Press.

Senger, Ö. (2011). Mann-Whitney, Kolmogorov-Smirnov and Wald-Wolfowitz tests type I Error with Monte Carlo Simulation study in terms of their rates and statistical power. karşılaştırılması. (Published Doctoral Dissertation). Erzurum: Atatürk University Social Institute of Sciences.