High order data sharpening for density estimation

被引：18

作者：

Hall, P

Minnotte, MC

机构：

[1] Australian Natl Univ, Ctr Math & Applicat, Canberra, ACT 0200, Australia

[2] Utah State Univ, Logan, UT 84322 USA

来源：

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY | 2002年 / 64卷

关键词：

bandwidth; bias reduction; kernel methods; local polynomial methods; mean-squared error; nonparametric curve estimation; transformation methods; wiggliness;

D O I：

10.1111/1467-9868.00329

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：

It is shown that data sharpening can be used to produce density estimators that enjoy arbitrarily high orders of bias reduction. Practical advantages of this approach, relative to competing methods, are demonstrated. They include the sheer simplicity of the estimators, which makes code for computing them particularly easy to write, very good mean-squared error performance, reduced 'wiggliness' of estimates and greater robustness against undersmoothing.

引用

页码：141 / 157

页数：17

共 19 条

[1] ADAPTIVE DENSITY FLATTENING - A METRIC DISTORTION PRINCIPLE FOR COMBATTING BIAS IN NEAREST NEIGHBOR METHODS [J].