基于LENQD序列生成的线性过程误差回归函数小波估计Berry-Esseen界

数学物理学报 ›› 2023, Vol. 43 ›› Issue (5): 1519-1528.

基于LENQD序列生成的线性过程误差回归函数小波估计Berry-Esseen界

李永明^1,^*(),庞伟才²(),李乃医³()

¹上饶师范学院数学与计算机科学学院江西上饶 334001
²南宁师范大学数学与统计学院南宁 530001
³广东海洋大学数学与计算机学院广东湛江 524088

收稿日期:2022-06-06 修回日期:2023-01-12 出版日期:2023-10-26 发布日期:2023-08-09
通讯作者: 李永明 E-mail:lym1019@163.com;pangweicai2021@163.com;linaiyi1979@163.com
作者简介:庞伟才，Email: pangweicai2021@163.com;|李乃医，Email:linaiyi1979@163.com
基金资助:
国家自然科学基金项目(12161074);江西省自然科学基金重点项目(20212ACB201006);广东省自然科学基金项目(2022A1515010978);上饶市科技计划(2020K006)

Berry-Esseen Bound of Wavelet Estimator for Regression Model with Linear Process Errors Generated by LENQD Sequence

Li Yongming^1,^*(),Pang Weicai²(),Li Naiyi³()

¹School of Mathematics and Computer Science, Jiangxi Shangrao Normal University, Jiangxi Shangrao 334001
²School of Mathematics and Statistics, Nanning Normal University, Nanning 530001
³School of Mathematics and Computer, Guangdong Ocean University, Guangdong Zhanjiang 524088

Received:2022-06-06 Revised:2023-01-12 Online:2023-10-26 Published:2023-08-09
Contact: Yongming Li E-mail:lym1019@163.com;pangweicai2021@163.com;linaiyi1979@163.com
Supported by:
NSFC(12161074);NSFJ(20212ACB201006);NSFG(2022A1515010978);Shangrao Science and Technology Talent Plan(2020K006)

摘要/Abstract

摘要：

在LENQD相依序列生产的线性过程误差下, 研究了固定设计非参数回归模型小波估计. 利用LENQD序列的矩不等式和特征函数不等式, 建立了未知回归函数小波估计的Berry-Esseen界. 通过选取适当的参数, 其界可达$O(n^{-1/6})$. 所得结果推广了相关文献的研究结果.

关键词: 固定设计回归模型, 线性过程, LENQD序列, 小波估计, Berry-Esseen界

Abstract:

Based on linear process random errors generated by LENQD random sequence, the wavelet estimator of nonparametric fixed design regression model is considered. By the characteristic function inequality and moment inequality of LENQD random sequence, the Berry-Esseen bounds of the wavelet estimator for unknown regression function are obtained. And by choosing some suitable constants, their bounds can reach $O(n^{-\frac{1}{6}})$. The obtained results generalize the corresponding results in recent literature.

Key words: Fixed design regression, Linear process, LENQD random sequence, Wavelet estimator, Berry-Esseen bound

中图分类号:

O212.7

李永明,庞伟才,李乃医. 基于LENQD序列生成的线性过程误差回归函数小波估计Berry-Esseen界[J]. 数学物理学报, 2023, 43(5): 1519-1528.

Li Yongming,Pang Weicai,Li Naiyi. Berry-Esseen Bound of Wavelet Estimator for Regression Model with Linear Process Errors Generated by LENQD Sequence[J]. Acta mathematica scientia,Series A, 2023, 43(5): 1519-1528.

参考文献

[1]	Georgiev A A. Local properties of function fitting estimates with application to system identication. Mathematical Statistics and Application, 1983, 2: 141-151
[2]	Georgiev A A. Consistent nonparametric multiple regression: The fixed design case. J Multivariate Anal, 1988, 25(1): 100-110
[3]	Roussas G G, Tran L T, Ioannides D A. Fixed design regression for time series: Asymptotic normality. J Multivariate Anal, 1992, 40(2): 262-291
[4]	杨善朝, 李永明. 强混合样本下回归加权估计的一致渐近正态性. 数学学报, 2006, 49A(5): 1163-1170
[4]	Yang S C, Li Y M. Uniformly asymptotic normality of the regression weighted estimator for strong mixing samples. Acta Math Sin, 2006, 49A(5): 1163-1170
[5]	Yang S C. Uniformly asymptotic normality of the regression weighted estimator for negatively associated samples. Stat Probab Lett, 2003, 62(2): 101-110
[6]	Liang H Y, Li Y Y. A Berry-Esseen type bound of regression estimator based on linear process errors. J Korean Math Soc, 2008, 45(6): 1753-1767
[7]	Ding L W, Chen P Y, Li Y M. Berry-Esseen bounds of weighted kernel estimator for a nonparametric regression model based on linear process errors under a LNQD sequence. J Inequal Appl, 2018, 2018(10): 1-12
[8]	Antoniadis A, Gregoire G, Mckeague I W. Wavelet methods for curve estimation. J Amer Stat Assoc, 1994, 89(428): 1340-1352
[9]	薛留根. 混合误差下回归函数小波估计的一致收敛速度. 数学物理学报, 2002, 22A(4): 528-535
[9]	Xue L G. Uniform convergence rates of the wavelet estimator of regression function under mixing error. Acta Math Sci, 2002, 22A(4): 528-535
[10]	孙燕, 柴根象. 固定设计下回归函数的小波估计. 数学物理学报, 2004, 24A(5): 597-606
[10]	Sun Y, Chai G X. Nonparametric wavelet estimation of a fixed designed regression function. Acta Math Sci, 2004, 24A(5): 597-606
[11]	Liang H Y, Qi Y Y. Asymptotic normality of wavelet estimator of regression function under NA assumptions. Bull Korean Math Soc, 2007, 44(2): 247-257
[12]	李永明, 尹长明, 韦程东. $\varphi$混合误差下回归函数小波估计的渐近正态性. 应用数学学报, 2008, 31(6): 1016-1055
[12]	Li Y M, Yin C M, Wei C D. On the asymptotic normality for $\varphi$-mixing dependent of wavelet regression function estimator. Acta Math Appl Sin, 2008, 31(6): 1016-1055
[13]	李永明, 韦程东. 强混合误差回归函数小波估计的Berry-Esseen界. 数学物理学报, 2009, 29A(5): 1453-1463
[13]	Li Y M, Wei C D. Berry-Esseen bounds for wavelet estimator of regression function under strong mixing process. Acta Math Sci, 2009, 29A(5): 1453-1463
[14]	Li Y M, Wei C D, Xin G D. Berry-Esseen bounds of wavelet estimator in a regression with linear process errors. Stat Probab Lett, 2011, 81(1): 103-111
[15]	李永明, 郭建华, 杨善朝. 一类混合序列生成的线性过程误差半参数回归模型小波估计的Berry-Esseen界. 应用数学学报, 2013, 36(6): 1021-1036
[15]	Li Y M, Guo J H, Yang S C. The Berry-Esseen bounds of wavelet estimators for semiparametric regression model whose errors form a linear process with a mixing innovations. Acta Math Appl Sin, 2013, 36(6): 1021-1036
[16]	Ding L W, Li Y M. The Berry-Esseen bounds of wavelet estimator for regression model whose errors form a linear process with a $\rho$-mixing. J Inequal Appl, 2016, 2016(107): 1-12
[17]	Ding L W, Chen P Y, Li Y M. Consistency for wavelet estimator in nonparametric regression model with extended negatively dependent samples. Stat Pap, 2020, 61(6): 2331-2349
[18]	Li Y M, Pang W C, Feng Z Q, Li N Y. On the linearly extended negative quadrant dependent random variables and its inequalities. Commun Stat Theor M, 2022, doi.org/10.1080/03610926.2022.2068600.
[19]	Petrov V V. Limit Theory for Probability Theory. New York: Oxford University Press, 1995