ASYMPTOTIC OPTIMALITY OF THE LEAST-SQUARES CROSS-VALIDATION BANDWIDTH FOR KERNEL ESTIMATES OF INTENSITY FUNCTIONS

被引：22

作者：

BROOKS, MM

MARRON, JS

机构：

[1] Department of Statistics, University of North Carolina, Chapel Hill

来源：

STOCHASTIC PROCESSES AND THEIR APPLICATIONS | 1991年 / 38卷 / 01期

基金：

美国国家科学基金会;

关键词：

BANDWIDTH SELECTION; INTENSITY FUNCTION; CROSS-VALIDATION BANDWIDTH; KERNEL ESTIMATION; NONSTATIONARY POISSON PROCESSES;

D O I：

10.1016/0304-4149(91)90076-O

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：

In this paper, kernel function methods are considered for estimating the intensity function of a nonhomogeneous Poisson process. A least-squares cross-validation bandwidth for the kernel intensity estimator is introduced, and it is proven that this bandwidth is asymptotically optimal for kernel intensity estimation.

引用

页码：157 / 165

页数：9

共 20 条

[1] NONPARAMETRIC INFERENCE FOR A FAMILY OF COUNTING PROCESSES [J].