Statistical inference for constant-stress accelerated life tests with dependent competing risks from Marshall-Olkin bivariate exponential distribution
Statistical inference for constant-stress accelerated life tests with dependent competing risks from Marshall-Olkin bivariate exponential distribution
复制标题
基于马歇尔-奥尔金二元指数分布的依赖竞争风险的恒定应力加速寿命试验的统计推断
DOI：
10.1002/qre.2582
复制
发表时间：
2020
影响因子：
2.3
通讯作者：
Zhang Chunfang
中科院分区：
文献类型：
--
作者：
Bai Xuchao;Shi Yimin;Liu Yiming;Zhang Chunfang
本文考虑了二类审查条件下的恒应力加速依赖竞争风险模型。竞争风险间的依赖结构采用Marshall-Olkin二元指数分布模型，加速模型采用幂规则模型描述。利用极大似然估计方法和自举抽样技术，得到了模型参数在任务时刻正常使用条件下的点估计和区间估计以及可靠性函数。采用基于关键量的估计方法对模型参数和广义置信区间进行估计。作为比较，我们还分别考虑了基于共轭先验和重要抽样方法的模型参数的Bayes估计和最高后验密度可信区间。为了说明所提出的方法，使用蒙特卡罗仿真来研究不同估计方法的性能。最后，对一个数据集进行了分析，并与原始结果进行了比较。
This paper considers a constant-stress accelerated dependent competing risks model under Type-II censoring. The dependent structure between competing risks is modeled by a Marshall-Olkin bivariate exponential distribution, and the accelerated model is described by the power rule model. The point and interval estimation of the model parameters and the reliability function under the normal usage condition at mission time are obtained by using the maximum likelihood estimation method and the bootstrap sampling technique. Moreover, the pivotal quantities based estimation are adopted to estimate the model parameters and the generalized confidence intervals. As a comparison, we also consider the Bayes estimation and the highest posterior density credible intervals for the model parameters based on conjugate priors and importance sampling method, respectively. To illustrate the proposed methodology, a Monte Carlo simulation is used to study the performances of different estimation methods. Finally, a dataset is analyzed for illustrative purpose and a comparison with the original results is also given.