Adaptive optimal kernel density estimation for directional data

被引：9
作者：
Thanh Mai Pham Ngoc [1 ]
机构：
[1] Univ Paris Saclay, Univ Paris Sud, CNRS, Lab Math Orsay, F-91405 Orsay, France
来源：
JOURNAL OF MULTIVARIATE ANALYSIS | 2019年 / 173卷
关键词：
Bandwidth selection; Directional data; Kernel density estimation; Oracle inequality; Penalization methods; BANDWIDTH SELECTION; RULE;
D O I：
10.1016/j.jmva.2019.02.009
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：
This paper considers nonparametric density estimation with directional data. A new rule is proposed for bandwidth selection for kernel density estimation. The procedure is automatic, fully data-driven, and adaptive to the degree of smoothness of the density. An oracle inequality and optimal rates of convergence for the L-2 error are derived. These theoretical results are illustrated with simulations. (C) 2019 Elsevier Inc. All rights reserved.
引用
收藏
页码：248 / 267
页数：20
相关论文
共 24 条
  • [1] On the Estimation of the Density of a Directional Data Stream
    Amiri, Aboubacar
    Thiam, Baba
    Verdebout, Thomas
    [J]. SCANDINAVIAN JOURNAL OF STATISTICS, 2017, 44 (01) : 249 - 267
  • [2] KERNEL ESTIMATORS OF DENSITY-FUNCTION OF DIRECTIONAL-DATA
    BAI, ZD
    RAO, CR
    ZHAO, LC
    [J]. JOURNAL OF MULTIVARIATE ANALYSIS, 1988, 27 (01) : 24 - 39
  • [3] ADAPTIVE DENSITY ESTIMATION FOR DIRECTIONAL DATA USING NEEDLETS
    Baldi, P.
    Kerkyacharian, G.
    Marinucci, D.
    Picard, D.
    [J]. ANNALS OF STATISTICS, 2009, 37 (6A) : 3362 - 3395
  • [4] Bartlett M.S., 1963, The Indian Journal of Statistics, Series A, V25, P245, DOI [10.2307/25049271, DOI 10.2307/25049271]
  • [5] Kernel density estimation on the torus
    Di Marzio, Marco
    Panzera, Agnese
    Taylor, Charles C.
    [J]. JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2011, 141 (06) : 2156 - 2173
  • [6] Kernel density estimation for directional-linear data
    Garcia-Portugues, Eduardo
    Crujeiras, Rosa M.
    Gonzalez-Manteiga, Wenceslao
    [J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2013, 121 : 152 - 175
  • [7] Exact risk improvement of band width selectors for kernel density estimation with directional data
    Garcia-Portugues, Eduardo
    [J]. ELECTRONIC JOURNAL OF STATISTICS, 2013, 7 : 1655 - 1685
  • [8] Universal pointwise selection rule in multivariate function estimation
    Goldenshluger, Alexander
    Lepski, Oleg
    [J]. BERNOULLI, 2008, 14 (04) : 1150 - 1190
  • [9] KERNEL DENSITY-ESTIMATION WITH SPHERICAL DATA
    HALL, P
    WATSON, GS
    CABRERA, J
    [J]. BIOMETRIKA, 1987, 74 (04) : 751 - 762
  • [10] Houdré C, 2003, PROG PROBAB, V56, P55
123