On the Modification of the Adaptive Test for Comparing Means
DOI:
https://doi.org/10.15678/ZNUEK.2015.0940.0401Keywords:
adaptive tests, permutation tests, comparing populations, Monte CarloAbstract
The paper presents a proposal of a modification of the L. Hao and D. Houser adaptive test for comparing the locations of two distributions. The modification is based on the linear combination of three test statistics. In the Hao and Houser test, due to the values of the robust asymmetry and shape characteristics, the test statistic is chosen. A method of continuous modification of the test statistic is presented. The properties of the proposed procedure are analyzed in a Monte Carlo study. The proposal could be used in quality control monitoring processes.Downloads
References
Domański C., Pruska K. [2000], Nieklasyczne metody statystyczne, PWE, Warszawa.
Efron B., Tibshirani R. [1993], An Introduction to the Bootstrap, Chapman & Hall/ CRC, Boca Raton, Washington, DC.
Good P. [2005], Permutation, Parametric, and Bootstrap Tests of Hypotheses, Springer, New York.
Hao L., Houser D. [2012], Adaptive Procedures for Wilcoxon-Mann-Whitney Test: Seven Decades of Advances, http://comp.uark.edu/~lhao/adaptive.pdf.
Hogg R.V., Fisher D.M., Randles R.H. [1975], A Two-sample Adaptive Distribution-free Test, „Journal of the American Statistical Associacion", vol. 70, http://dx.doi.org/10.2307/2285950.
O'Gorman T.W. [2012], Adaptive Tests of Significance Using Permutations of Residuals with R and SAS, John Wiley and Sons, New Jersey.
Sheskin D.J. [2003], Handbook of Parametric and Nonparametric Statistical Procedures, Chapman & Hall, Boca Raton.
