An Improved Online Penalty Parameter Selection Procedure for $\ell_1$-Penalized Autoregressive with Exogenous Variables

Many recent developments in the high-dimensional statistical time series literature have centered around time-dependent applications that can be adapted to regularized least squares. Of particular interest is the lasso, which both serves to regularize and provide feature selection. The lasso require...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nicholson, William B, Yan, Xiaohan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Nicholson, William B
Yan, Xiaohan
description Many recent developments in the high-dimensional statistical time series literature have centered around time-dependent applications that can be adapted to regularized least squares. Of particular interest is the lasso, which both serves to regularize and provide feature selection. The lasso requires the specification of a penalty parameter that determines the degree of sparsity to impose. The most popular penalty parameter selection approaches that respect time dependence are very computationally intensive and are not appropriate for modeling certain classes of time series. We propose enhancing a canonical time series model, the autoregressive model with exogenous variables, with a novel online penalty parameter selection procedure that takes advantage of the sequential nature of time series data to improve both computational performance and forecast accuracy relative to existing methods in both a simulation and empirical application involving macroeconomic indicators.
doi_str_mv 10.48550/arxiv.2010.07594
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2010_07594</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2010_07594</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-eaf229dd0c5b426b2d0503c819220dc432e2cb0e1e9250aaa9937e79bce958713</originalsourceid><addsrcrecordid>eNotkD1rwzAURbV0KGl_QKdqyOpUlq3YGk1I20AghoZOBfMsPacCWQryR5L--iZupwsX7oF7CHmK2SLNhWAvEM5mXHB2LVgmZHpPToWjm_YY_Iia7pw1DmmJDmx_oSUEaLHHQD_QouqNd7QMXqEeAtLGBzr_QmureB5NE_NzZRRD7wMeAnadGZGeTP9N12d_QOeHjn5CMFBb7B7IXQO2w8f_nJH963q_eo-2u7fNqthGsMzSCKHhXGrNlKhTvqy5ZoIlKo8l50yrNOHIVc0wRskFAwApkwwzWSuUIs_iZEae_7DT8-oYTAvhUt0MVJOB5BebZFf5</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>An Improved Online Penalty Parameter Selection Procedure for $\ell_1$-Penalized Autoregressive with Exogenous Variables</title><source>arXiv.org</source><creator>Nicholson, William B ; Yan, Xiaohan</creator><creatorcontrib>Nicholson, William B ; Yan, Xiaohan</creatorcontrib><description>Many recent developments in the high-dimensional statistical time series literature have centered around time-dependent applications that can be adapted to regularized least squares. Of particular interest is the lasso, which both serves to regularize and provide feature selection. The lasso requires the specification of a penalty parameter that determines the degree of sparsity to impose. The most popular penalty parameter selection approaches that respect time dependence are very computationally intensive and are not appropriate for modeling certain classes of time series. We propose enhancing a canonical time series model, the autoregressive model with exogenous variables, with a novel online penalty parameter selection procedure that takes advantage of the sequential nature of time series data to improve both computational performance and forecast accuracy relative to existing methods in both a simulation and empirical application involving macroeconomic indicators.</description><identifier>DOI: 10.48550/arxiv.2010.07594</identifier><language>eng</language><subject>Statistics - Applications ; Statistics - Machine Learning ; Statistics - Methodology</subject><creationdate>2020-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2010.07594$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2010.07594$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Nicholson, William B</creatorcontrib><creatorcontrib>Yan, Xiaohan</creatorcontrib><title>An Improved Online Penalty Parameter Selection Procedure for $\ell_1$-Penalized Autoregressive with Exogenous Variables</title><description>Many recent developments in the high-dimensional statistical time series literature have centered around time-dependent applications that can be adapted to regularized least squares. Of particular interest is the lasso, which both serves to regularize and provide feature selection. The lasso requires the specification of a penalty parameter that determines the degree of sparsity to impose. The most popular penalty parameter selection approaches that respect time dependence are very computationally intensive and are not appropriate for modeling certain classes of time series. We propose enhancing a canonical time series model, the autoregressive model with exogenous variables, with a novel online penalty parameter selection procedure that takes advantage of the sequential nature of time series data to improve both computational performance and forecast accuracy relative to existing methods in both a simulation and empirical application involving macroeconomic indicators.</description><subject>Statistics - Applications</subject><subject>Statistics - Machine Learning</subject><subject>Statistics - Methodology</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotkD1rwzAURbV0KGl_QKdqyOpUlq3YGk1I20AghoZOBfMsPacCWQryR5L--iZupwsX7oF7CHmK2SLNhWAvEM5mXHB2LVgmZHpPToWjm_YY_Iia7pw1DmmJDmx_oSUEaLHHQD_QouqNd7QMXqEeAtLGBzr_QmureB5NE_NzZRRD7wMeAnadGZGeTP9N12d_QOeHjn5CMFBb7B7IXQO2w8f_nJH963q_eo-2u7fNqthGsMzSCKHhXGrNlKhTvqy5ZoIlKo8l50yrNOHIVc0wRskFAwApkwwzWSuUIs_iZEae_7DT8-oYTAvhUt0MVJOB5BebZFf5</recordid><startdate>20201015</startdate><enddate>20201015</enddate><creator>Nicholson, William B</creator><creator>Yan, Xiaohan</creator><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20201015</creationdate><title>An Improved Online Penalty Parameter Selection Procedure for $\ell_1$-Penalized Autoregressive with Exogenous Variables</title><author>Nicholson, William B ; Yan, Xiaohan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-eaf229dd0c5b426b2d0503c819220dc432e2cb0e1e9250aaa9937e79bce958713</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Statistics - Applications</topic><topic>Statistics - Machine Learning</topic><topic>Statistics - Methodology</topic><toplevel>online_resources</toplevel><creatorcontrib>Nicholson, William B</creatorcontrib><creatorcontrib>Yan, Xiaohan</creatorcontrib><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Nicholson, William B</au><au>Yan, Xiaohan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An Improved Online Penalty Parameter Selection Procedure for $\ell_1$-Penalized Autoregressive with Exogenous Variables</atitle><date>2020-10-15</date><risdate>2020</risdate><abstract>Many recent developments in the high-dimensional statistical time series literature have centered around time-dependent applications that can be adapted to regularized least squares. Of particular interest is the lasso, which both serves to regularize and provide feature selection. The lasso requires the specification of a penalty parameter that determines the degree of sparsity to impose. The most popular penalty parameter selection approaches that respect time dependence are very computationally intensive and are not appropriate for modeling certain classes of time series. We propose enhancing a canonical time series model, the autoregressive model with exogenous variables, with a novel online penalty parameter selection procedure that takes advantage of the sequential nature of time series data to improve both computational performance and forecast accuracy relative to existing methods in both a simulation and empirical application involving macroeconomic indicators.</abstract><doi>10.48550/arxiv.2010.07594</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2010.07594
ispartof
issn
language eng
recordid cdi_arxiv_primary_2010_07594
source arXiv.org
subjects Statistics - Applications
Statistics - Machine Learning
Statistics - Methodology
title An Improved Online Penalty Parameter Selection Procedure for $\ell_1$-Penalized Autoregressive with Exogenous Variables
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T17%3A32%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20Improved%20Online%20Penalty%20Parameter%20Selection%20Procedure%20for%20$%5Cell_1$-Penalized%20Autoregressive%20with%20Exogenous%20Variables&rft.au=Nicholson,%20William%20B&rft.date=2020-10-15&rft_id=info:doi/10.48550/arxiv.2010.07594&rft_dat=%3Carxiv_GOX%3E2010_07594%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true