جستجوی مقالات مرتبط با کلیدواژه "progressive censoring" در نشریات گروه "آمار"

An important challenge in using progressive Type-II right censoring is to determine a removal scheme. It can be predetermined or randomly chosen per discrete distributions. This paper considers the random removal problem and proposes two scenarios for determining the removal vector without introducing any parameter to a model when progressively Type-II censored samples are available from the three-parameter Weibull distribution. The proposed scenarios are based on the normalized spacings with random and fixed coefficients according to progressively Type-II censored order statistics from an exponential distribution. The joint probability mass functions of removal vectors are provided as well as expected experimental time under the proposed two methods. Moreover, the maximum likelihood estimators (MLEs) and corrected maximum likelihood estimators (corrected MLEs) of parameters are obtained. The new approaches are compared with the patterns of removal derived from the discrete uniform and binomial distributions using a Monte Carlo simulation study. This comparison is based on their estimated biases, estimated mean squared errors and expected total time on the experiment. Finally, a real data example is given to show the practical applications of the paper.

In this paper, the probability of failure-free operation until time t, along with the probability of stress-strength, based on progressive censoring data is studied in a family of lifetime distributions. Since the number of data in a progressive censoring scheme is usually reduced, so shrinkage methods have been used to improve the classical estimator. For estimation purposes, the preliminary test and Stein-type shrinkage estimators are proposed and their exact distributional properties are derived. For numerical superiority demonstration of the proposed estimation strategies, some improved bootstrap confidence intervals, are constructed. The theoretical results are illustrated by a real data examples and an extensive simulation study. Simulation shreds of evidence revealed that our proposed shrinkage strategies perform well in the estimation of parameters based on progressive censoring data.

We consider a stage life testing model and assume that the information at which levels the failures occurred is not available. In order to find estimates for the lifetime distribution parameters, we propose an EM-algorithm approach which interprets the lack of knowledge about the stages as missing information. Furthermore, we illustrate the implementation difficulties caused by an increasing number of stages. The study is supplemented by a data example as well as simulations.