独立随机序列均值多变点的非参数检测  

A Nonparametric Test for Multiple Changes in the Mean of Independent Random Series

作　　者：秦瑞兵[1,2] 田铮[2] 陈占寿[2,3] 

机构地区：[1]山西大学数学科学学院,太原030006 [2]西北工业大学应用数学系,西安710072 [3]青海师范大学数学系,西宁810008

出　　处：《应用概率统计》2013年第5期449-457,共9页Chinese Journal of Applied Probability and Statistics

基　　金：自然科学基金数学天元青年基金(11226217);自然科学基金青年基金项目(11301291);第51批中国博士后科学基金面上资助(2012M510772);中国博士后科学基金第六批特别资助项目(2013T60266)资助

摘　　要：本文考虑独立随机序列均值多变点的检测与估计问题,提出一种非参数的检验方法,给出其渐近分布,同时亦给出了变点位置的估计,并证明了变点个数估计的一致性.Monte Carlo试验研究了该检验统计量的有限样本性质,结果表明该统计量对于厚尾误差具有较好势和经验水平.最后将文中所给的非参数检验方法应用到鲁北化工(LBC)股票价格数据中,结果表明,文中所给统计量可以准确检验出多变点并进行估计.A nonpaxametric procedure is proposed to detect multiple changes in the mean of independent random series and the asymptotic distribution is derived. Simultaneously, the estimators for the locations of the change points axe obtained. Moreover, the performance of the test is studied by Monte Carlo simulation, which demonstrates that the proposed test has high powers and good sizes for heavy-tailed innovations. Finally, the feasibility of the proposed test is illustrated by the application on the LBC data of stock prices.

关 键 词：独立随机序列 多变点 非参数检验 样本中位数 

分 类 号：O212.1[理学—概率论与数理统计]