Minimax risk inequalities for the location-parameter classification problem

被引：1

作者：

Allaart, PC ^{[1
]}

机构：

[1] Vrije Univ Amsterdam, Amsterdam, Netherlands

来源：

JOURNAL OF MULTIVARIATE ANALYSIS | 1998年 / 66卷 / 02期

关键词：

optimal-partitioning; minimax risk; classification; partition range; convexity theorem; concentration function; tail concentration;

D O I：

10.1006/jmva.1998.1748

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：

Minimax risk inequalities are obtained for the location-parameter classification problem. For the classical single observation case with continuous distributions, best possible bounds are given in terms of their Levy concentration, establishing a conjecture of Hill and Tong (1989). In addition, sharp bounds for the minimax risk are derived for the multiple (i.i.d.) observations case, based on the tail concentration and the Levy concentration. Some Fairly sharp bounds for discontinuous distributions are also obtained. (C) 1998 Academic Press.

引用

页码：255 / 269

页数：15

共 10 条

[1]

ALLAART PC, UNPUB

[2]

[Anonymous], 1951, PACIFIC J MATH

[3]

[Anonymous], 1973, CONCENTRATION FUNCTI

[4]

Ferguson TS., 1967, Mathematical statistics: A decision theoretic approach