END样本最近邻密度估计的一致强相合速度

2014-03-06 05:40兰冲锋吴群英
吉林大学学报(理学版) 2014年3期
关键词:密度估计群英相依

兰冲锋,吴群英

(1.阜阳师范学院 经济与管理学院,安徽 阜阳 236037;2.桂林理工大学 理学院,广西 桂林 541004)

0 引 言

对每个n=1,2,…和所有的x1,x2,…,xn∈R都成立,则称随机变量{Xn;n≥1}是END的.

文献[12]中例4.1表明,END序列不仅反应了负相依结构,而且在某种程度上体现了正相依结构,是一种非常广泛的相依随机变量序列.如:当M=1时,END序列即为ND序列.显然,END序列包含了独立序列,而文献[14]举例说明了NA序列一定是ND序列,但ND序列不一定是NA序列,而ND序列又是END序列,反之则不成立.表明END序列是比独立序列、NA序列和ND序列更弱的、更广泛的一种随机变量序列.Shen[15]研究了END序列的概率不等式及其应用,而对于END样本下的最近邻密度估计问题,目前尚未见文献报道.基于此,本文考虑END样本最近邻密度估计的一致强相合速度问题,在更弱的条件下,得到了与NA序列相同的结论,从而推广了文献[7]的结果.本文用“≪”表示“O”.

1 引 理

2 主要结果

注1 1)定理1在更弱的条件下,得到了与NA样本情形下相同的结论;2)由推论1可知,fn(x)的一致强相合收敛速度几乎为n-1/6,该结论与NA样本情形下是相同的,但与独立情形的n-1/4不同.

[1]Loftsgaarden D O,Quesenberry C D.A Nonparametric Estimate of a Multivariate Density Function[J].Ann Math Statist,1965,36(3):1049-1051.

[2]Wagner T J.Stronger Consistency of a Nonparametric Estimate of a Density Function[J].IEEE Trans Systems Man Cybernet,1973,3(3):289-290.

[3]陈希孺.最近邻密度估计的收敛速度 [J].中国科学:A辑,1981(12):1419-1428.(CHEN Xiru.The Rate of Consistency of Nearest Neighbor Density Estimator[J].Science in China:Ser A,1981(12):1419-1428.)

[4]Devroye L P,Wagner T J.The Strong Uniform Consistency of Nearest Neighbor Density Estimates[J].Ann Math Statist,1977,5(3):536-540.

[5]CHEN Xiru.The Rate of Uniformly Consistency of Nearest Neighbor Density Estimator[J].J Mathematical Research and Exposition,1983,3(1):61-68.

[6]柴根象.平稳序列最近邻密度估计的相合性 [J].数学学报,1989,32(3):423-432.(CHAI Genxiang.Consistency of Nearest Neighbor Density Estimator of Stationary Processes[J].Acta Mathematica Sinica,1989,32(3):423-432.)

[7]杨善朝.NA样本最近邻密度估计的相合性 [J].应用数学学报,2003,26(3):385-395.(YANG Shanchao.Consistency of Nearest Neighbor Estimator of Density Function for Negatively Associated Samples [J].Acta Mathematicae Applicatae Sinica,2003,26(3):385-395.)

[8]倪展,吴群英,施生塔.ND序列下最近邻密度估计的强相合速度 [J].山东大学学报:理学版,2012,47(12):6-9.(NI Zhan,WU Qunying,SHI Shengta.The Rate of Strong Consistency of Nearest Neighbor Density Estimator for ND Samples[J].Journal of Shandong University:Natural Science,2012,47(12):6-9.)

[9]刘艳,吴群英.ND样本最近邻密度估计的一致强相合性 [J].华侨大学学报:自然科学版,2012,33(5):590-594.(LIU Yan,WU Qunying.Uniform Strong Consistency of Nearest Neighbor Estimator of Density Function for Negative Dependent Samples[J].Journal of Huaqiao University:Natural Science,2012,33(5):590-594.)

[10]刘永辉,吴群英.ND样本最近邻密度估计的相合性 [J].吉林大学学报:理学版,2012,50(6):1141-1145.(LIU Yonghui,WU Qunying.Consistency of Nearest Neighbor Estimator of Density Function for Negative Dependent Samples[J].Journal of Jilin University:Science Edition,2012,50(6):1141-1145.)

[11]施生塔,吴群英,倪展.ND样本最近邻密度估计的一致强相合速度 [J].桂林理工大学学报,2012,32(4):631-634.(SHI Shengta,WU Qunying,NI Zhan.Rate of Strong Uniform Consistency of Nearest Neighbor Density Estimator for Negative Dependent Samples[J].Journal of Guilin University of Technology,2012,32(4):631-634.)

[12]LIU Li.Precise Large Deviations for Dependent Random Variables with Heavy Tails[J].Stat Prob Lett,2009,79(9):1290-1298.

[13]LIU Li.Necessary and Sufficient Conditions for Moderate Deviations of Dependent Random Variables with Heavy Tails[J].Sci China:Math,2010,53(6):1421-1434.

[14]WU Qunying.Complete Convergence for Negatively Dependent Sequences of Random Variables[J/OL].Journal of Inequalities and Applications,2010,doi:10.1155/2010/507293.

[15]SHEN Aiting.Probability Inequalities for END Sequence and Their Applications[J/OL].Journal of Inequalities and Applications,2011,doi:10.1186/1029-242X-2011-98.

[16]吴群英.混合序列的概率极限理论 [M].北京:科学出版社,2006:23.(WU Qunying.Probability Limit Theory of Mixing Sequences[M].Beijing:Science Press,2006:23.)

猜你喜欢
密度估计群英相依
m-NOD样本最近邻密度估计的相合性
面向鱼眼图像的人群密度估计
基于MATLAB 的核密度估计研究
一种基于改进Unet的虾苗密度估计方法
家国两相依
相守相依
2009,新武器群英荟
Almost Sure Convergence of Weighted Sums for Extended Negatively Dependent Random Variables Under Sub-Linear Expectations
相依相随
相依相伴