多重Ⅰ型混合截尾样本的Weibull分布参数估计  

Type⁃ⅠHybrid Censoring of Multiple Samples Based on Weibull Distribution

作　　者：秦睿 QIN Rui(College of Mathematics and Statistics,Guangxi Normal University,Guilin 541004,China)

机构地区：[1]广西师范大学数学与统计学院,广西桂林541004

出　　处：《广西民族大学学报（自然科学版）》2021年第4期64-69,共6页Journal of Guangxi Minzu University ：Natural Science Edition

摘　　要：在多重Ⅰ型混合截尾样本情形下,讨论了两参数威布尔分布的参数估计问题。首先结合样本次序统计量联合密度函数给出了参数最大似然估计的表达式,其次利用Newton⁃Raphson迭代方法得到参数的最大似然估计,然后借助指数分布给出参数的精确置信区间,最后对参数的最大似然估计进行模拟研究和实例案例分析,最大似然估计的稳定性和有效性得到验证。The original data is supposed to be obtained as failure times from k≥2 independent Type⁃I hybrid censoring systems.For the scale parameterλand shape parameter c of Weibull distribution,we derive the maximum likelihood estimator of scale parameterλand shape parameter c by Maximum Likelihood Estimate.Then Estimated value is obtained by using Newton Raphson iterative method.Furthermore,we propose exact confidence interval of parameters by using exponential distribution.Applicability and stability are illustrated by simulations as well as by example.

关 键 词：多重Ⅰ型混合截尾 WEIBULL分布 最大似然估计 

分 类 号：O212.1[理学—概率论与数理统计]