The accuracy and the computational complexity of a multivariate binned kernel density estimator

被引：18

作者：

Holmström, L ^{[1
]}

机构：

[1] Univ Helsinki, Rolf Nevanlinna Inst, Helsinki, Finland

[2] George Mason Univ, Ctr Computat Stat, Fairfax, VA 22030 USA

来源：

JOURNAL OF MULTIVARIATE ANALYSIS | 2000年 / 72卷 / 02期

基金：

美国国家科学基金会;

关键词：

kernel density estimation; binning; estimation error; computational complexity;

D O I：

10.1006/jmva.1999.1863

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：

The computational cost of multivariate kernel density estimation can be reduced by prebinning the data. The data are discretized to a grid and a weighted kernel estimator is computed. We report results on the accuracy of such a binned kernel estimator and discuss the computational complexity of the estimator as measured by its average number of nonzero terms. (C) 2000 Academic Press.

引用

页码：264 / 309

页数：46

共 23 条

[1]

Adams A, 2003, SOBOLEV SPACES

[2]

[Anonymous], 1971, FOURIER ANAL EUCLIDE

[3]

[Anonymous], 1992, MULTIVARIATE DENSITY

[4]

[Anonymous], 1964, Handbook of mathematical functions

[5]

[Anonymous], REAL COMPLEX ANAL

[6]

Bhattacharya RN., 1976, NORMAL APPROXIMATION

[7]

BREUER K, 1990, THESIS FACHBEREICH S

[8]

Davis P.J., 1967, NUMERICAL INTEGRATIO

[9]

Devroye L., 1987, A course in density estimation

[10]

Fan J., 1994, Journal of computational and graphical statistics, V3, P35, DOI 10.2307/1390794

← 1 2 3 →