Asymptotically local minimax estimation of infinitely smooth density with censored data

被引：7

作者：

Belitser, E

Levit, B

机构：

[1] Vrije Univ Amsterdam, Dept Math, NL-1081 HV Amsterdam, Netherlands

[2] Univ Utrecht, Math Inst, NL-3584 CD Utrecht, Netherlands

来源：

ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS | 2001年 / 53卷 / 02期

关键词：

efficient estimator; local minimax risk; Kaplan-Meier estimator; kernel; random censorship;

D O I：

10.1023/A:1012418722154

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 [统计学]; 070103 [概率论与数理统计]; 0714 [统计学];

摘要：

The problem of the nonparametric minimax estimation of an infinitely smooth density at a given point, under random censorship, is considered. We establish the exact asymptotics of the local minimax risk and propose the efficient kernel-type estimator based on the well known Kaplan-Meier estimator.

引用

页码：289 / 306

页数：18

共 16 条

[1]

Andersen P. K., 2012, Statistical models based on counting processes

[2]

Efficient estimation of analytic density under random censorship [J].