Reliability Estimation : From Classical to Bayesian Approach
by
M. Pandey
Department of Zoology, Banaras Hindu University

Statistical reliability is comparatively a recent discipline in the area of statistical theory. Reliability theory concerns in particular in the evaluation of the performance of a system or a subsystem or a component. The initial literature mostly describes classical estimation procedures (cf. Mann Schafer and Singpurwalla (1974), Barlow and Proschan(1975) and Lawless(1982)) and mentions in brief Bayesian techniques also. Martz and Waller (1982) gave the first detailed Bayesian approach to reliability estimation. This paper tries to give the evolution of the reliability estimation methodology starting from Pandey (1982) to Pandey and Chandra (2002) and Pandey and Shomvanshi (2002) from classical to Bayesian through preliminary test estimators, adaptive estimators, Bayes estimators and concatenated adaptive Bayesian estimators. The reliability problems considered are with well known failure models, some new failure models, stress-strength models, a form of accelerated life testing problems using multiple stresses and in software reliability growth models.

Date received: October 6, 2002

Copyright © 2002 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # cais-35.