A Review and Comparison of Bandwidth Selection Methods for Kernel Regression

被引：46

作者：

Koehler, Max ^{[1
]}

Schindler, Anja ^{[1
]}

Sperlich, Stefan ^{[2
,3
]}

机构：

[1] Univ Gottingen, Fac Econ Sci, D-37073 Gottingen, Germany

[2] Univ Geneva, Dept Sci Econ, CH-1211 Geneva, Switzerland

[3] Univ Geneva, Res Ctr Stat, CH-1211 Geneva, Switzerland

来源：

INTERNATIONAL STATISTICAL REVIEW | 2014年 / 82卷 / 02期

基金：

瑞士国家科学基金会;

关键词：

Kernel regression; bandwidth selection; plug-in; cross-validation; SMOOTHING PARAMETER; VARIABLE BANDWIDTH; CROSS-VALIDATION; BOOTSTRAP; ERROR;

D O I：

10.1111/insr.12039

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：

Over the last decades, several methods for selecting the bandwidth have been introduced in kernel regression. They differ quite a bit, and although there already exist more selection methods than for any other regression smoother, one can still observe coming up new ones. Given the need of automatic data-driven bandwidth selectors for applied statistics, this review is intended to explain and, above all, compare these methods. About 20 different selection methods have been revised, implemented and compared in an extensive simulation study.

引用

页码：243 / 274

页数：32

共 50 条

[1] Selection of bandwidth for kernel regression
Kolacek, Jan
Horova, Ivanka
[J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2016, 45 (05) : 1487 - 1500
[2] Bandwidth selection for kernel binomial regression
Okumura, Hidenori
Naito, Kanta
[J]. JOURNAL OF NONPARAMETRIC STATISTICS, 2006, 18 (4-6) : 343 - 356
[3] Comparison of bandwidth selection methods for kernel smoothing of ROC curves
Zhou, XH
Harezlak, J
[J]. STATISTICS IN MEDICINE, 2002, 21 (14) : 2045 - 2055
[4] Consistent bandwidth selection for kernel binary regression
Altman, N
MacGibbon, B
[J]. JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1998, 70 (01) : 121 - 137
[5] Bandwidth selection for kernel regression with correlated errors
Lee, Young Kyung
Mammen, Enno
Park, Byeong U.
[J]. STATISTICS, 2010, 44 (04) : 327 - 340
[6] A COMPARISON OF BANDWIDTH AND KERNEL FUNCTION SELECTION IN GEOGRAPHICALLY WEIGHTED REGRESSION FOR HOUSE VALUATION
Yacim, Joseph Awoamim
Boshoff, Douw Gert Brand
[J]. INTERNATIONAL JOURNAL OF TECHNOLOGY, 2019, 10 (01) : 58 - 68
[7] COMPARISON OF GEOMETRIC AND ARITHMETIC MEANS FOR BANDWIDTH SELECTION IN NADARAYA-WATSON KERNEL REGRESSION ESTIMATOR
Xu, Li-Yuan
Zhang, Min
Zhu, Wei
He, Yu-Lin
[J]. PROCEEDINGS OF 2013 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC), VOLS 1-4, 2013, : 999 - 1004
[8] Sequential Bayesian bandwidth selection for multivariate kernel regression with applications
Li, Yong
Zhang, Mingzhi
Zhang, Yonghui
[J]. ECONOMIC MODELLING, 2022, 112
[9] A comparative review of bandwidth selection for kernel density estimation
Chiu, ST
[J]. STATISTICA SINICA, 1996, 6 (01) : 129 - 145
[10] Optimal bandwidth selection for semi-recursive kernel regression estimators
Slaoui, Yousri
[J]. STATISTICS AND ITS INTERFACE, 2016, 9 (03) : 375 - 388

← 1 2 3 4 5 →