Yuzhu Tian, Qianqian Zhu, Maozai Tian

【Abstract】

The type-II progressively hybrid censoring scheme can be deemed as a mixture of typeII progressive and hybridcensoring schemes, which has been utilized to analyze lifetime data in the literature for exponential distribution and Weibull distribution and so on, where the experiment terminates at a pre-specified time. However, little attention has been paid to parametric estimation under this censoring scheme for the mixed exponentialdistribution (MED) model, which is an important model in life data analysis. Based on typeII progressively hybridcensored samples, the estimation problem of the MED is addressed. The closed form of maximum likelihood estimators (MLEs) of unknown parameters using the EM algorithm are obtained. Some Monte Carlo simulations are implemented and a real data set is analyzed to illustrate the performance of the proposed method. (C) 2015 Elsevier B.V. All rights reserved.

【Keywords】

mixed exponential distribution (MED), Type-II progressively hybrid censoring, EM algorithm