Adaptive estimation of the mode of a multivariate density

被引：17

作者：

Klemelä, J ^{[1
]}

机构：

[1] Univ Mannheim, Dept Stat, Econ Fac, D-68131 Mannheim, Germany

来源：

JOURNAL OF NONPARAMETRIC STATISTICS | 2005年 / 17卷 / 01期

关键词：

adaptive curve estimation; bandwidth selection; kernel estimation; minimax risk;

D O I：

10.1080/10485250410001723151

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：

Estimation of the location of the mode of a multivariate density function is studied. We use the maximizer of a kernel estimator as an estimator for the location of the mode and we discuss the choice of the smoothing parameter of the kernel estimator to be maximized. This smoothing parameter is chosen in an adaptive way, that is, without assuming knowledge of the smoothness of the density function. It is proved that the proposed method has the optimal adaptive rate of convergence.

引用

页码：83 / 105

页数：23

共 23 条

[1]

[Anonymous], 1979, CONTRIBUTIONS STAT

[2] The adaptive rate of convergence in a problem of pointwise density estimation [J].

Butucea, C .

STATISTICS & PROBABILITY LETTERS, 2000, 47 (01) :85-90

[3]

BUTUCEA C, 2000, MATH METHODS STAT, V9, P39

[4] GEOMETRIZING RATES OF CONVERGENCE .3. [J].

DONOHO, DL ;

LIU, RC .

ANNALS OF STATISTICS, 1991, 19 (02) :668-701

[5] SOME DIRECT ESTIMATES OF THE MODE [J].

GRENANDER, U .

ANNALS OF MATHEMATICAL STATISTICS, 1965, 36 (01) :131-138

[6]

Grund B, 1995, ANN STAT, V23, P2264

[7]

KEPSKI OV, 1991, THEORY PROBABILITY I, V36, P682

[8]

Klemelä J, 2001, ANN STAT, V29, P1567

[9]

KONAKOV VD, 1973, THEORY PROBABILITY I, V18, P794

[10]

LEPSKII OV, 1992, THEOR PROBAB APPL+, V37, P433

← 1 2 3 →