Generalized least squares cross-validation in kernel density estimation

被引：4
|
作者：
Zhang, Jin [1 ]
机构：
[1] Yunnan Univ, Sch Math & Stat, Kunming 650091, Yunnan, Peoples R China
来源：
STATISTICA NEERLANDICA | 2015年 / 69卷 / 03期
关键词：
bandwidth; integrated squared error; normal mixture; oversmoothing; undersmoothing; NORMAL REFERENCE BANDWIDTH; SELECTION;
D O I：
10.1111/stan.12061
中图分类号：
O21 [概率论与数理统计]; C8 [统计学];
学科分类号：
020208 ; 070103 ; 0714 ;
摘要：
The kernel density estimation is a popular method in density estimation. The main issue is bandwidth selection, which is a well-known topic and is still frustrating statisticians. A robust least squares cross-validation bandwidth is proposed, which significantly improves the classical least squares cross-validation bandwidth for its variability and undersmoothing, adapts to different kinds of densities, and outperforms the existing bandwidths in statistical literature and software.
引用
收藏
页码：315 / 328
页数：14
相关论文
共 50 条
12345