基于记录值的逆威布尔分布参数统计推断  

Statistical Inference on Parameters of Inverse Weibull Distribution Based on Record Values

作　　者：段李永 于秀君 王涛 

机构地区：[1]云南师范大学数学学院,云南 昆明

出　　处：《统计学与应用》2022年第2期346-353,共8页Statistical and Application

摘　　要：本文基于下记录值样本,研究了两参数逆威布尔分布模型的点估计和区间估计问题。基于构造的服从卡方分布的枢轴量导出了参数的逆矩估计,同时得到了形状参数的传统等尾置信区间和最短置信区间以及形状参数和尺度参数的联合置信域,最后通过数值实例将得到的区间和已有文献基于构造的服从F分布的枢轴量得到的区间进行比较以说明本文方法的优良性。In this paper, point estimation and confidence intervals estimation of inverse Weibull distribution model with two parameters are studied based on the sample of lower record values. The inverse moment estimator of parameters is derived based on the structure of pivotal quantities subject to the chi-square distribution, and at the same time, the traditional equal tailed confidence interval and the shortest confidence interval of shape parameter, as well as the joint confidence field of shape and scale parameters, are obtained. Finally, a numerical example is given to compare the obtained intervals with the obtained intervals based on the structure of pivot quantities subject to F distribution in the existing literature, so as to illustrate the superiority of the method in this paper.

关 键 词：逆威布尔分布 记录值 枢轴量 置信区间 联合置信域 

分 类 号：O212.1[理学—概率论与数理统计]