×

An empirical power comparison of three tests of exponentiality under mixture- and outlier-models. (English) Zbl 0705.62046

Summary: We present the results of an empirical power study of three prominent goodness-of-fit tests for exponentiality due to S. S. Shapiro and M. B. Wilk [Technometrics 14, 355-370 (1972; Zbl 0234.62030)], J. Durbin [Biometrika 62, 5-22 (1975; Zbl 0297.62027)], and M. L. Tiku [Aust. J. Stat. 22, 260-275 (1980; Zbl 0459.62032)] by considering the mixture- and the outlier-exponential models as alternatives. This study is on similar lines as those of D. Dyer and M. S. Harbin [J. Stat. Comput. Simulation 12, 277-291 (1981; Zbl 0476.62048)] and N. Balakrishnan [ibid. 18, 265-272 (1983)]. We show that Tiku’s test is on the whole considerably more powerful than the other two tests.

MSC:

62G10 Nonparametric hypothesis testing
62Q05 Statistical tables
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] 1987: Order statistics from mixture- and outlier-exponential models and some applications, M. S. Thesis, McMaster University, Hamilton, Ontario, Canada.
[2] Balakrishnan, J. Statist. Comput. Simul. 18 pp 265– (1983)
[3] Durbin, Biometrika 62 pp 5– (1975)
[4] Dyer, J. Statist. Comput. Simul. 12 pp 277– (1981)
[5] Shapiro, Technometrics 14 pp 355– (1972)
[6] Tiku, Commun. Statist. 3 pp 777– (1974)
[7] Tiku, Austra l. J. Statist. 22 pp 260– (1980) · Zbl 0459.62032 · doi:10.1111/j.1467-842X.1980.tb01175.x
[8] , and , 1986: Robust Inference. Marcel Dekker, New York.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.