在逐次Ⅱ型截尾样本下,讨论以Gumbel极值分布为边缘分布,Gumbel Copula为连接函数的相依竞争失效模型参数的极大似然估计(MLE)和Bayes估计.对于参数MLE,提出与生存函数成正比的两阶段估计(Inference for the margins,IFM).对于Bayes估计...在逐次Ⅱ型截尾样本下,讨论以Gumbel极值分布为边缘分布,Gumbel Copula为连接函数的相依竞争失效模型参数的极大似然估计(MLE)和Bayes估计.对于参数MLE,提出与生存函数成正比的两阶段估计(Inference for the margins,IFM).对于Bayes估计,证明了Gumbel极值分布尺度参数的对数凹性,采用混合ARS(Adaptive Re-jection Sampling Algorithm)和MH(Metropolis-Hastings)抽样方法实现参数估计.模拟结果表明,当两失效机理关联性较弱时,两种估计结果相差不大,但关联性提高时,Bayes估计优于IFM估计.展开更多
This paper mainly study extreme values of FGM random sequences.We prove a technique theorem by the dependence structure of FGM sequences,and further obtain the limiting distributions of maxima and k-th largest for sta...This paper mainly study extreme values of FGM random sequences.We prove a technique theorem by the dependence structure of FGM sequences,and further obtain the limiting distributions of maxima and k-th largest for stationary FGM random sequences.展开更多
文摘在逐次Ⅱ型截尾样本下,讨论以Gumbel极值分布为边缘分布,Gumbel Copula为连接函数的相依竞争失效模型参数的极大似然估计(MLE)和Bayes估计.对于参数MLE,提出与生存函数成正比的两阶段估计(Inference for the margins,IFM).对于Bayes估计,证明了Gumbel极值分布尺度参数的对数凹性,采用混合ARS(Adaptive Re-jection Sampling Algorithm)和MH(Metropolis-Hastings)抽样方法实现参数估计.模拟结果表明,当两失效机理关联性较弱时,两种估计结果相差不大,但关联性提高时,Bayes估计优于IFM估计.
文摘This paper mainly study extreme values of FGM random sequences.We prove a technique theorem by the dependence structure of FGM sequences,and further obtain the limiting distributions of maxima and k-th largest for stationary FGM random sequences.
