| 厚尾相依序列的均值变点估计 |
| |
| 引用本文： | 韩四儿,田铮,王红军.厚尾相依序列的均值变点估计[J].应用概率统计,2008,24(4):337-344. |
| |
| 作者姓名： | 韩四儿 田铮 王红军 |
| |
| 作者单位： | 1. 西北工业大学应用数学系,西安,710072
2. 西北工业大学应用数学系,西安,710072;模式识别国家重点实验室,中国科学院自动化研究所,北京,100080 |
| |
| 摘 要： | 本文研究了厚尾相依序列的均值变点估计. 证明了变点的CUSUM估计的一致性并得到了收敛速度.在方差无穷的情况下推广了H\'{a}jek--R\'{e}nyi不等式.
|
| 关 键 词： | 变点估计 厚尾 H\'{a}jek-R\'{e}nyi不等式. |
Change-Point in the Mean of Heavy-Tailed Dependent Observations |
| |
| Han Sier,Tian Zheng,Wang Hongjun.Change-Point in the Mean of Heavy-Tailed Dependent Observations[J].Chinese Journal of Applied Probability and Statisties,2008,24(4):337-344. |
| |
| Authors: | Han Sier Tian Zheng Wang Hongjun |
| |
| Institution: | Department of Mathematics, Northwestern Polytechnical University; National Key Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
| |
| Abstract: | This paper studies the problem of mean change point in heavy-tailed dependent observations. We prove the consistency of CUSUM estimator of change-point and derive the rate of convergence. A H\'{a}jek-R\'{e}nyi type inequality is also proved. Results are obtained under weak moment assumptions. |
| |
| Keywords: | Change-point estimation heavy-tails |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《应用概率统计》浏览原始摘要信息 |
| 点击此处可从《应用概率统计》下载免费的PDF全文 |
