Bayesian Reliability Estimation of Single Component Under Accelerated Life Testing
by
Navin Chandra
Department of Statistics,Banaras Hindu University,Varanasi-221 005,INDIA
Coauthors: Dr. Manju Pandey (Department of Zoology,Banaras Hindu University,Varanasi-221 005,INDIA)

BAYESIAN RELIABILITY ESTIMATION OF SINGLE COMPONENT UNDER ACCELERATED LIFE TESTING:

Several Components have a long-life under the few circumstances where these products are being used in the environmental conditions. Especially for extremely reliable Components/Items it is in general not possible to make life tests under usual stress because testing time would exceed the available time. Therefore applying the multiple stresses simultaneously on the component is more realistic for getting failure data in short time and may be considered a form of Accelerated Life Testing (ALT). ALT determines the life distribution of component on the basis of failure data and is helpful for predicting the reliability of the components/items.

This paper provides the Bayes and quasi-Bayes estimation of reliability of single component under stress-strength of Burr distribution. We consider ‘c’ and ‘k’ have independent inverted gamma prior with parameters (a1, b1) and (a2, b2) respectively. The Bayes and quasi-Bayes estimators of reliability are compared on the basis of relative efficiency and absolute bias of the said estimators. Numerical study has been done for the various combinations of Burr and prior parameters by generating 200 Monte-Carlo samples.

Date received: October 17, 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-56.