In this paper, the parameters and reliability characteristics of the mixture of the failure time distribution are estimated based on a complete sample using both Markov chain Monte Carlo (MCMC) method and maximum likelihood estimation via cross-entropy (CE) algorithm. While maximum likelihood estimation is the most frequently used method for parameter estimation, MCMC has recently emerged as a good alternative. The most popular MCMC method, called the Metropolis-Hastings algorithm, is used to provide a complete analysis of the concerned posterior distribution. A simulation study is provided to compare MCMC with CE, and differences between the estimates obtained by the two approaches are evaluated.
Financed by the National Centre for Research and Development under grant No. SP/I/1/77065/10 by the strategic scientific research and experimental development program:
SYNAT - “Interdisciplinary System for Interactive Scientific and Scientific-Technical Information”.