Bayesian Reliability Estimation: State of the Art for the Time-Dependent Case

摘要

The four types of reliability estimation techniques considered in this report are nonparametric, classical, Bayes, and empirical Bayes. Point and interval estimators of reliability for exponential and Weibull data are considered for the time-dependent case in which the resulting estimators are functionally dependent on time. A set of exponential data is used for illustrating and comparing the different estimators. The assumptions underlying each type of es¬timation are given to provide an awareness of the costs and benefits associated with each technique.