Cross-Validation in Nonparametric Regression with Outliers
A popular data-driven method for choosing the bandwidth in standard kernel regression is cross-validation. Even when there are outliers ill the data, robust kernel regression can be used to estimate the unknown regression curve [Robust and Nonlinear Time Series Analysis. Lecture Notes in Statist. (1...
Saved in:
Main Author: | |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2005
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/soe_research/127 https://ink.library.smu.edu.sg/context/soe_research/article/1126/viewcontent/euclid.aos.1132936564.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.soe_research-1126 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.soe_research-11262019-07-22T13:48:17Z Cross-Validation in Nonparametric Regression with Outliers Leung, Denis H. Y. A popular data-driven method for choosing the bandwidth in standard kernel regression is cross-validation. Even when there are outliers ill the data, robust kernel regression can be used to estimate the unknown regression curve [Robust and Nonlinear Time Series Analysis. Lecture Notes in Statist. (1984) 26 163-184]. However, Under these Circumstances Standard cross-validation is no longer a satisfactory bandwidth selector because it is unduly influenced by extreme prediction errors caused by the existence of these Outliers. A more robust method proposed here is a cross-validation method that discounts the extreme prediction errors. In large samples the robust method chooses consistent bandwidths, and the consistency of the method is practically independent of the form ill which extreme prediction errors are discounted. Additionally, evaluation of the method's finite sample behavior in a simulation demonstrates that the proposed method performs favorably. This method call also be applied to other problems, for example, model selection, that require cross-validation. 2005-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/soe_research/127 info:doi/10.1214/009053605000000499 https://ink.library.smu.edu.sg/context/soe_research/article/1126/viewcontent/euclid.aos.1132936564.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Economics eng Institutional Knowledge at Singapore Management University Bandwidth cross-validation kernel nonparametric regression robust smoothing Econometrics |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Bandwidth cross-validation kernel nonparametric regression robust smoothing Econometrics |
spellingShingle |
Bandwidth cross-validation kernel nonparametric regression robust smoothing Econometrics Leung, Denis H. Y. Cross-Validation in Nonparametric Regression with Outliers |
description |
A popular data-driven method for choosing the bandwidth in standard kernel regression is cross-validation. Even when there are outliers ill the data, robust kernel regression can be used to estimate the unknown regression curve [Robust and Nonlinear Time Series Analysis. Lecture Notes in Statist. (1984) 26 163-184]. However, Under these Circumstances Standard cross-validation is no longer a satisfactory bandwidth selector because it is unduly influenced by extreme prediction errors caused by the existence of these Outliers. A more robust method proposed here is a cross-validation method that discounts the extreme prediction errors. In large samples the robust method chooses consistent bandwidths, and the consistency of the method is practically independent of the form ill which extreme prediction errors are discounted. Additionally, evaluation of the method's finite sample behavior in a simulation demonstrates that the proposed method performs favorably. This method call also be applied to other problems, for example, model selection, that require cross-validation. |
format |
text |
author |
Leung, Denis H. Y. |
author_facet |
Leung, Denis H. Y. |
author_sort |
Leung, Denis H. Y. |
title |
Cross-Validation in Nonparametric Regression with Outliers |
title_short |
Cross-Validation in Nonparametric Regression with Outliers |
title_full |
Cross-Validation in Nonparametric Regression with Outliers |
title_fullStr |
Cross-Validation in Nonparametric Regression with Outliers |
title_full_unstemmed |
Cross-Validation in Nonparametric Regression with Outliers |
title_sort |
cross-validation in nonparametric regression with outliers |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2005 |
url |
https://ink.library.smu.edu.sg/soe_research/127 https://ink.library.smu.edu.sg/context/soe_research/article/1126/viewcontent/euclid.aos.1132936564.pdf |
_version_ |
1770569027563814912 |