الفهرس 
Designing bayesian reliability sampling plans for weibull lifetime models using censored failure data
AbstractOnly 14 pages are availabe for public view
 |  | from | 180 |  |  |
| | | from | 180 | | |
Abstract
Reliability sampling plans are often used to determine the compliance of the product with relevant quality standards and customers{u2019} expectations and needs. This study presents Bayesian reliability sampling plans for the Weibull distribution based on progressively Type-II censored data with binomial removals. In constructing the sampling plans the decision theoretic approach is used. A dependent bivariate non-conjugate prior is used for the scale and shape parameters. The total cost of the sampling plan consists of the sampling, time-consuming, rejection, and acceptance costs. Two decision rules are used to determine lot acceptability. The first rule is based on the Bayes estimator of the survival function, while the second depends on the Bayes estimator of the mean lifetime. The Bayes estimators are obtained under both the quadratic and LINEX error loss assumptions using the Metropolis-within-Gibbs Markov Chain Monte Carlo (MCMC) algorithm. Simulations for evaluating the Bayes risk are carried out and the optimal sampling plans are reported for various sample sizes, observed number of failures, binomial removal probabilities, minimum acceptable reliability, and minimum acceptable average lifetime. Sensitivity of the proposed plans is performed. Bayesian prediction for future order statistics is also used to derive life test acceptance criteria. The proposed approaches are illustrated using real data sets