Spline Single-Index Prediction Model

For the past two decades, single-index model, a special case of projection pursuit regression, has proven to be an efficient way of coping with the high dimensional problem in nonparametric regression. In this paper, based on weakly dependent sample, we investigate the single-index prediction (SIP)...

Full description

Bibliographic Details
Main Authors: Wang, Li, Yang, Lijian
Format: Report
Language:unknown
Published: arXiv 2007
Subjects:
Statistics Theory math.ST
FOS Mathematics
Primary 62G08; Secondary 62M10
Iceland
Online Access:https://dx.doi.org/10.48550/arxiv.0704.0302
https://arxiv.org/abs/0704.0302
id ftdatacite:10.48550/arxiv.0704.0302
record_format openpolar
spelling ftdatacite:10.48550/arxiv.0704.0302 2023-05-15T16:49:55+02:00 Spline Single-Index Prediction Model Wang, Li Yang, Lijian 2007 https://dx.doi.org/10.48550/arxiv.0704.0302 https://arxiv.org/abs/0704.0302 unknown arXiv Assumed arXiv.org perpetual, non-exclusive license to distribute this article for submissions made before January 2004 http://arxiv.org/licenses/assumed-1991-2003/ Statistics Theory math.ST FOS Mathematics Primary 62G08; Secondary 62M10 Preprint Article article CreativeWork 2007 ftdatacite https://doi.org/10.48550/arxiv.0704.0302 2022-04-01T15:31:54Z For the past two decades, single-index model, a special case of projection pursuit regression, has proven to be an efficient way of coping with the high dimensional problem in nonparametric regression. In this paper, based on weakly dependent sample, we investigate the single-index prediction (SIP) model which is robust against deviation from the single-index model. The single-index is identified by the best approximation to the multivariate prediction function of the response variable, regardless of whether the prediction function is a genuine single-index function. A polynomial spline estimator is proposed for the single-index prediction coefficients, and is shown to be root-n consistent and asymptotically normal. An iterative optimization routine is used which is sufficiently fast for the user to analyze large data of high dimension within seconds. Simulation experiments have provided strong evidence that corroborates with the asymptotic theory. Application of the proposed procedure to the rive flow data of Iceland has yielded superior out-of-sample rolling forecasts. : 39 pages,5 figures Report Iceland DataCite Metadata Store (German National Library of Science and Technology)
institution Open Polar
collection DataCite Metadata Store (German National Library of Science and Technology)
op_collection_id ftdatacite
language unknown
topic Statistics Theory math.ST
FOS Mathematics
Primary 62G08; Secondary 62M10
spellingShingle Statistics Theory math.ST
FOS Mathematics
Primary 62G08; Secondary 62M10
Wang, Li
Yang, Lijian
Spline Single-Index Prediction Model
topic_facet Statistics Theory math.ST
FOS Mathematics
Primary 62G08; Secondary 62M10
description For the past two decades, single-index model, a special case of projection pursuit regression, has proven to be an efficient way of coping with the high dimensional problem in nonparametric regression. In this paper, based on weakly dependent sample, we investigate the single-index prediction (SIP) model which is robust against deviation from the single-index model. The single-index is identified by the best approximation to the multivariate prediction function of the response variable, regardless of whether the prediction function is a genuine single-index function. A polynomial spline estimator is proposed for the single-index prediction coefficients, and is shown to be root-n consistent and asymptotically normal. An iterative optimization routine is used which is sufficiently fast for the user to analyze large data of high dimension within seconds. Simulation experiments have provided strong evidence that corroborates with the asymptotic theory. Application of the proposed procedure to the rive flow data of Iceland has yielded superior out-of-sample rolling forecasts. : 39 pages,5 figures
format Report
author Wang, Li
Yang, Lijian
author_facet Wang, Li
Yang, Lijian
author_sort Wang, Li
title Spline Single-Index Prediction Model
title_short Spline Single-Index Prediction Model
title_full Spline Single-Index Prediction Model
title_fullStr Spline Single-Index Prediction Model
title_full_unstemmed Spline Single-Index Prediction Model
title_sort spline single-index prediction model
publisher arXiv
publishDate 2007
url https://dx.doi.org/10.48550/arxiv.0704.0302
https://arxiv.org/abs/0704.0302
genre Iceland
genre_facet Iceland
op_rights Assumed arXiv.org perpetual, non-exclusive license to distribute this article for submissions made before January 2004
http://arxiv.org/licenses/assumed-1991-2003/
op_doi https://doi.org/10.48550/arxiv.0704.0302
_version_ 1766040094843600896

Similar Items