删失样本下的极值指数估计  

On Estimation for Extreme Value Index Under Censored Sample

作　　者：朱雅楠 陈守全[1] ZHU Ya-nan;CHEN Shou-quan(School of Mathematics and Statistics, Southwest University, Chongqing 400715, China)

机构地区：[1]西南大学数学与统计学院,重庆400715

出　　处：《西南师范大学学报（自然科学版）》2021年第1期148-152,共5页Journal of Southwest China Normal University(Natural Science Edition)

基　　金：国家自然科学基金项目(11571283).

摘　　要：应用删失回归方法,给出了重尾分布极值指数的一种估计量,得到了这种估计量及其对应极值分位数估计量的渐近正态性.数值模拟结果显示,新估计量的均方误差较现有估计量明显减小.An estimator of the extreme value index of the heavy-tailed distribution has been given by censored regression.The asymptotic normality of the estimator and its corresponding extreme quantile estimator have been obtained.Numerical simulation results show that the mean square error of the new estimator is significantly smaller than the existing estimators.

关 键 词：极值指数 重尾分布 删失回归 

分 类 号：O211.4[理学—概率论与数理统计]