ON THE CONSISTENCY OF THE GLOBAL MINIMIZER OF MALLOWS CRITERION FOR NONPARAMETRIC REGRESSION

被引：0
|
作者：
CHIU, ST
机构：
[1] ACAD SINICA,INST STAT SCI,TAIPEI 11529,TAIWAN
[2] COLORADO STATE UNIV,DEPT STAT,FT COLLINS,CO 80523
来源：
JOURNAL OF STATISTICAL PLANNING AND INFERENCE | 1991年 / 27卷 / 02期
关键词：
NONPARAMETRIC REGRESSION; KERNEL ESTIMATE; BANDWIDTH SELECTION; FOURIER TRANSFORM; PERIODGRAM;
D O I：
10.1016/0378-3758(91)90017-9
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 purpose of this work is to solve an open problem suggested by Rice (1984) concerning the consistency of the global minimizer of Mallows' criterion. Mallows' criterion has been used for selecting the smoothing parameter for nonparametric regression. Rice (1984) showed that the local minimizer of Mallows' criterion on any compact interval containing the optimal bandwidth is (weakly) consistent. In this paper, the consistency of the global minimizer of Mallows' criterion is established.
引用
收藏
页码：223 / 230
页数：8
相关论文
共 50 条
12345