The Application of Taylor Expansion to Error Density Estimation Nonparametric Regression

被引：0
|
作者：
Zeng Qingjian [1 ]
Li Qing [1 ]
机构：
[1] Guangdong Songshan Polytech Coll, Shaoguan 512126, Guangdong, Peoples R China
来源：
FOURTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2012) | 2012年 / 8334卷
关键词：
Taylor Expansion; Nonparametric Regression; Error Density; Kernel Density Estimation; Smoothing Parameter;
D O I：
10.1117/12.954151
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In this paper, by applying the Taylor expansion, the authors study the asymptotic properties of the kernel density estimation (f) over dot(x)(e)of an unknown error distribution function f (e) in a nonparametric regression model. Then, they study the choice of the smoothing parameters in the estimation (f) over dot(x)(e). Finally, an approximation confidence interval of f (e) was given.
引用
收藏
页数：5
相关论文
共 50 条
12345