Some Competing Accelerated Life Testing Models with a Bayesian Perspective*
2 / 1
Authors
-
Debaraj Sen
Department of Mathematics and Statistics, Concordia University, Montréal, Québec, Canada
-
Yogendra P. Chaubey
Department of Mathematics and Statistics, Concordia University, Montréal, Québec, Canada
-
Murari Singh
Formerly at Department of Statistics, University of Toronto, Toronto, Ontario, Canada
Keywords:
: Inverse Gaussian Model; Log-normal Model; Gamma Model; Coefficient of Variation; Bayesian ApproachAbstract
Several competing accelerated life testing models have been studied for modeling accelerated failure times by many authors (see Meeker and Escobar,
1998). This article briefly reviews several aspects and properties of some competing accelerated life testing models namely the log-normal, the
inverse Gaussian and the gamma models which are widely recognized in reliability theory. In these situations, modeling of the mean time to failure is
modeled as a function of the stress variable, while assuming other parameter(s) to be constant. In this paper we considered the modeling of coefficient
of variation also as a function of the stress variable, that has not been considered in the literature, in the best knowledge of the authors. We propose a
Bayesian approach for finding a point estimate as well as credible interval estimate for the coefficient of variation under the assumption that the data
are drawn from one of the above mentioned distributions
Downloads
References
Bhattacharyya, G. K. and Fries, A. (1982). Inverse Gaussian regression
and accelerated life tests, Survival Analysis (eds. J.Crowly and
R.A. Johnson, IMS lecture notes-monograph series-2, Institute of
Mathematical Statistics, Hayward, California, 101-118.
Chaubey, Y.P., Singh M., and Sen D. (2017). Symmetrizing and variance
stabilizing transformations of sample coefficient of variation from
inverse Gaussian distribution. Sankhya¯ B79, 217-246.
Chaubey, Y.P., Singh M., Sen D., and Sarker, A. (2022). Bayesian
Inference for a Common CV from Inverse Gaussian Distributions,
Poster presented at ISBA, 2022, June 26 - July 1, 2022, Montreal.
Chhikara, R. S. and Folks, J. L. (1977). The inverse Gaussian
distribution as a lifetime model. Technometrics 19(2), 461-468.
Chhikara, R. S. and Folks, J. L. (1989). The inverse Gaussian
distribution. Marcel Dekker, New York. 19(2), 461-468.
Das, M.N. (1958). Reinforced incomplete block designs. Journal of the
Indian Society of Agricultural Statistics. 10 73-77.
Escobar, L.A. and Meeker, W.Q. (2006.) A review of accelerated test
models. Statistical Science 21 552-577.
Gnedenko, B. Pavlov, I. and Ushakov, I. (1999). Statistical Reliability
Engineering. Wiley, New York.
Ihaka, R., and Gentleman, R. (1996). R: A language for data analysis
and graphics. Journal of Computational and Graphical Statistics
5, 299-314.
Johnson, N. L., Kotz, S. and Balakrishnan, N. (1994). Distributions in
Statistics: Continuous Univariate Distributions -1, 2nd Edition.
John Wiley & Sons, New York.
Johnson, N. L., and Welch, B. L. (1940). Applications of the non-central
t-distribution. Biometrika 31, 362-381.
Meeker, W.Q. and Escobar, L.A. (1998). Statistical Methods for
Reliability Data. Wiley, New York.
Nelson, W.B. (1971). Analysis of accelerated life test data, Part-1:
Numerical methods and test planning. IEEE Transactions on
Electrical Insulation EI-6, 165-181.
Nelson, W.B. (1975). Analysis of accelerated life test data, Least squares
methods for the Inverse Power Law Model. IEEE Transactions on
Reliability R-24, 103-107.
Sen D., and Chaubey, Y.P. (2011). A class of accelerated life testing
models based on the Gamma distributions. Journal of the Indian
Society of Agricultural Statistics 65, 155–161.
Singh, M. (1993). Behavior of sample coefficient of variation drawn
from several distributions Sankhya 55, 65-76.
Downloads
Submitted
Published
Issue
Section
How to Cite
