Adaptive smoothing for a penalized NPMLE of a non-increasing density

被引：21

作者：

Sun, JY ^{[1
]}

Woodroofe, M ^{[1
]}

机构：

[1] UNIV MICHIGAN,DEPT STAT,ANN ARBOR,MI 48109

来源：

JOURNAL OF STATISTICAL PLANNING AND INFERENCE | 1996年 / 52卷 / 02期

基金：

美国国家科学基金会;

关键词：

Brownian motion; non-parametric maximum likelihood; simulation; strong approximation;

D O I：

10.1016/0378-3758(95)00114-X

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：

A penalized version of the well-known non-parametric maximum likelihood estimator of a non-increasing density f has been developed recently. The penalized version depends on a smoothing parameter, as well as the data. Here some adaptive choices of the smoothing parameter are considered. The asymptotically optimal smoothing parameter depends on f through beta = -1/2F(0)f'(0). In the adaptive procedures, estimates of beta are used to determine the smoothing parameter. Two such procedures are shown to be theoretically correct and practically viable.

引用

页码：143 / 159

页数：17