By Topic

On Bayes Estimation for Mixtures of Two Exponential-Life-Distributions from Right-Censored Samples

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Papadapoulos, A.S. ; University of North Carolina, Charlotte ; Padgett, W.J.

In life testing and reliability estimation, the underlying failure time distribution need not be homogeneous. It can be a mixture of two distinct lifetime distributions due to two different failure modes. A failure-time distribution is assumed which is the mixture of two exponential distributions. Estimation of the two scale parameters, the mixing parameter, and the reliability is considered. MLEs, and Bayes estimators with respect to proper priors and to Jeffreys' vague priors, are given based on right-censored data. The right-censorship considered here includes types I & I and random right-censoring as special cases. Monte Carlo simulation indicates that the proper Bayes estimators are best with respect to root mean square error (RMSE) under the assumed priors and that the MLEs perform weli overall and are quite satisfactory in practice. The Bayes estimators with respect to Jeffreys' vague priors for the scale parameters do not perform as well as the MLE in the sense of RMSE and tend to have a greater bias.

Published in:

Reliability, IEEE Transactions on  (Volume:35 ,  Issue: 1 )