Summary
A procedure is proposed in this paper for testing the shape parameter, β of the Weibull distribution. The test statistic which is based on the extremal quotient, possesses a monotone property which makes it possible for rejection earlier than the last planned observation of the null hypothesis,H 0: β=β0 when the alternative hypothesis isH a: β<β0 and early acceptance ofH 0 whenH a: β>β0. The test being scale-free, does not require the scale parameter to be known.
Similar content being viewed by others
References
Engelhardt, M.E., andL.J. Bain: Some complete sampling results for the Weibull or extreme value distribution. Technometries15, 1973, 541–549.
Gumbel, E.J., andL.H. Herback: The exact distribution of the extremal quotient. Ann. Math. Statist.22, 1951, 418–426.
Gumbel, E.J., andR.D. Keeney The extremal quotient. Ann. Math. Statist.21, 1950, 523–538.
Izenman, A.J.: On the extremal quotient from a gamma sample. Biometrika63, 1976, 185–190.
Klimko, L.A.: et al., Upper bounds for the power of variant tests for the exponential distribution with Weibull alternatives. Technometrics17, 1975, 357–360.
Lieblein, J., andM. Zelen: Statistical investigation of the fatigue life of groove ball bearnings. Journal of Research, National Bureau of Standards57, 1956., 273–316.
Mann, N.R., R.E. Schafer andN.D. Singpurwalla: Methods for statistical analysis of reliability and life dara. New York 1974.
Weibull, W.: A statistical distribution function of wide applicability. J. App. Mech.18, 1951, 293–297.
Wong, P.G., andS.P. Wong: An extremal quotient test for exponential distribution. Metrika26, 1979, 1–4.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wong, P.G., Wong, S.P. A curtailed test for the shape parameter of the Weibull distribution. Metrika 29, 203–209 (1982). https://doi.org/10.1007/BF01893380
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01893380