极值估计中基于熵的门限值选取方法  

A Method of Selecting the Threshold Based on the Shannon Entropy in the Estimation of the Extreme Value Index

作　　者：袁明霞[1] 王丙均[2] 王晓谦[3] 

机构地区：[1]南京大学金陵学院,南京210089 [2]金陵科技学院基础部,南京211169 [3]南京师范大学数学与计算机科学学院,南京210097

出　　处：《淮阴工学院学报》2009年第3期1-5,共5页Journal of Huaiyin Institute of Technology

基　　金：江苏省高校自然科学基金资助项目(07KJD110093)

摘　　要：基于判别信息和Shannon熵的理论,使用图像法研究了门限值与次序统计量的熵的关系,给出了广义帕累托模型下门限值的选取方法。并针对广义帕累托分布进行模拟,得到了理想的结果。A new method of selecting the threshold from the other point of view is presented. As is well known, the data analyzed should involve more information about the tail index. So, we researched the relation between the threshold and the Shannon entropy of order statistics based on the theory of discrimination information and Shannon entropy. The method of how to select suitable threshold in generalized pareto models is put forward. Then,the generalized pareto distribution is simulated and ideal results are attained.

关 键 词：极值指数 次序统计量 门限值 判别信息 Shannon熵 

分 类 号：O211[理学—概率论与数理统计]