| Summary: | 碩士 === 國立中央大學 === 統計研究所 === 101 === Problems in series systems usually assume the lifetime distributions of components are independent. In this thesis, we consider to model the lifetime of a twocomponent series system under Type-1 censoring scheme by the Marshall-Olkin bivariate Weibull distribution. It is often to include masked data in which the component that causes the system to fail is not observed. When the data are masked or censored, there exist missing variables in the model. We apply the EM-algorithm to find the MLEs of the unknown parameters. In addition, we calculate the Fisher information via missing information principle to approximate the standard errors of the MLEs. Furthermore, we extend these results to the constant and step-stress accelerated life tests. Statistical inference on the lifetime distribution as the mean lifetimes, reliability functions and the quantiles of system and components are derived. Simulation study shows that the proposed methods perform accurately. A real data set is analyzed successfully.
|
|---|
