Kernel Selection in Nonparametric Regression

H. Halconruy; N. Marie

doi:10.3103/S1066530720010044

Kernel Selection in Nonparametric Regression

H. Halconruy
, N. Marie

Research output: Contribution to journal › Article › peer-review

Abstract

Abstract: In the regression model Y = b(X) + σ(X)ε, where X has a density f, this paper deals with an oracle inequality for an estimator of bf, involving a kernel in the sense of Lerasle et al. [13], selected via the PCO method. In addition to the bandwidth selection for kernel-based estimators already studied in Lacour et al. [12] and Comte and Marie [3], the dimension selection for anisotropic projection estimators of f and bf is covered.

Original language	English
Pages (from-to)	32-56
Number of pages	25
Journal	Mathematical Methods of Statistics
Volume	29
Issue number	1
DOIs	https://doi.org/10.3103/S1066530720010044
Publication status	Published - 1 Jan 2020

Keywords

model selection
nonparametric estimators
projection estimators
regression model

Access to Document

10.3103/S1066530720010044

Cite this

@article{201b50b4f36347598a233edfcf736371,

title = "Kernel Selection in Nonparametric Regression",

abstract = "Abstract: In the regression model Y = b(X) + σ(X)ε, where X has a density f, this paper deals with an oracle inequality for an estimator of bf, involving a kernel in the sense of Lerasle et al. [13], selected via the PCO method. In addition to the bandwidth selection for kernel-based estimators already studied in Lacour et al. [12] and Comte and Marie [3], the dimension selection for anisotropic projection estimators of f and bf is covered.",

keywords = "model selection, nonparametric estimators, projection estimators, regression model",

author = "H. Halconruy and N. Marie",

note = "Publisher Copyright: {\textcopyright} 2020, Allerton Press, Inc.",

year = "2020",

month = jan,

day = "1",

doi = "10.3103/S1066530720010044",

language = "English",

volume = "29",

pages = "32--56",

journal = "Mathematical Methods of Statistics",

issn = "1066-5307",

number = "1",

}

TY - JOUR

T1 - Kernel Selection in Nonparametric Regression

AU - Halconruy, H.

AU - Marie, N.

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Abstract: In the regression model Y = b(X) + σ(X)ε, where X has a density f, this paper deals with an oracle inequality for an estimator of bf, involving a kernel in the sense of Lerasle et al. [13], selected via the PCO method. In addition to the bandwidth selection for kernel-based estimators already studied in Lacour et al. [12] and Comte and Marie [3], the dimension selection for anisotropic projection estimators of f and bf is covered.

AB - Abstract: In the regression model Y = b(X) + σ(X)ε, where X has a density f, this paper deals with an oracle inequality for an estimator of bf, involving a kernel in the sense of Lerasle et al. [13], selected via the PCO method. In addition to the bandwidth selection for kernel-based estimators already studied in Lacour et al. [12] and Comte and Marie [3], the dimension selection for anisotropic projection estimators of f and bf is covered.

KW - model selection

KW - nonparametric estimators

KW - projection estimators

KW - regression model

U2 - 10.3103/S1066530720010044

DO - 10.3103/S1066530720010044

M3 - Article

AN - SCOPUS:85113942787

SN - 1066-5307

VL - 29

SP - 32

EP - 56

JO - Mathematical Methods of Statistics

JF - Mathematical Methods of Statistics

IS - 1

ER -

Kernel Selection in Nonparametric Regression

Abstract

Keywords

Access to Document

Fingerprint

Cite this