We present the general results determining confidence limits for the mean of exponential distribution in any time-sequential samples, which are obtained in any sequential life tests with replacement or without replace...We present the general results determining confidence limits for the mean of exponential distribution in any time-sequential samples, which are obtained in any sequential life tests with replacement or without replacement. Especially, we give the best lower confidence limits in the case of no failure data.展开更多
This article develops a new method, named M-Bayesian credible limit method, to estimate reliability parameter. In the article, the M-Bayesian credible limit method of failure rate is derived for zero-failure data from...This article develops a new method, named M-Bayesian credible limit method, to estimate reliability parameter. In the article, the M-Bayesian credible limit method of failure rate is derived for zero-failure data from products with exponential distribution. Relations between M-Bayesian credible limit and other classical confidence limits are discussed. Finally, the new method is applied to a real zero-failure data set, and as can be seen, it is both efficient and easy to operate.展开更多
基金the National Natural Science Foundation of China(Grant No.10471007)and MCSEC grant.
文摘We present the general results determining confidence limits for the mean of exponential distribution in any time-sequential samples, which are obtained in any sequential life tests with replacement or without replacement. Especially, we give the best lower confidence limits in the case of no failure data.
基金This work was supported partly by the Fujian Province Natural Science Foundation of Chinapartly by the Fujian University of Technology of China
文摘This article develops a new method, named M-Bayesian credible limit method, to estimate reliability parameter. In the article, the M-Bayesian credible limit method of failure rate is derived for zero-failure data from products with exponential distribution. Relations between M-Bayesian credible limit and other classical confidence limits are discussed. Finally, the new method is applied to a real zero-failure data set, and as can be seen, it is both efficient and easy to operate.