具有竞争风险的步进应力加速寿命试验的最优设计和Bayes估计  

Optimum plan and Bayesian estimation for step-stress accelerated lifetest with competition risk

作　　者：韦程东 何国源 陈少凡 WEI Cheng-dong;HE Guo-yuan;CHEN Shao-fan(School of Mathematics and Statistics,Nanning Normal University,Nanning 530023,China;School of Economics and Management,Hezhou University,Hezhou 542899,China;The Editorial Office of Guangxi Sciences,Guangxi Academy of Sciences,Nanning 530007,China)

机构地区：[1]南宁师范大学数学与统计学院,广西南宁530023 [2]贺州学院经济与管理学院,广西贺州542899 [3]广西科学院《广西科学》编辑部,广西南宁530007

出　　处：《高校应用数学学报（A辑）》2023年第3期266-276,共11页Applied Mathematics A Journal of Chinese Universities(Ser.A)

基　　金：国家自然科学基金(11561010)。

摘　　要：讨论了渐进II型截尾数据中具有竞争风险的步进应力加速寿命试验的最优试验设计和参数估计.通过假定产品寿命服从Weibull分布,尺度参数对数是应力水平的线性函数基础上,利用KH模型采用极大似然方法和Bayes方法对模型参数进行了点估计和区间估计,而最优试验设计是使尺度参数对数的极大似然估计值在正常应力水平下的渐进方差达到最小.最后进行了仿真研究,结果显示提出的估计量具有良好的稳健性和有效性.In this paper,the optimum test plan and parameter estimation of step-stress accel-erated life test with competitive risk in progressive type II censored data are discussed.It is assumed that product life follows a Weibull distribution with logarithm of scale parameter is a linear function of stress level.Based on the KH model,we use the maximum likelihood methods and Bayesian methods to generate the point estimations and interval estimations of the model parameters.And the optimal plan design is to minimize the gradual variance of the maximum likelihood estimation value of the logarithm of scale parameter at normal stress level.Finally,there is a simulation study.The results of the simulation show that the proposed estimation is robust and effective.

关 键 词：加速寿命试验 竞争风险 渐进II型截尾 最优试验设计 KH模型 

分 类 号：O213.2[理学—概率论与数理统计]