Publication:
On projection methods for functional time series forecasting

Simple item page
dc.affiliation.dptoUC3M. Departamento de Estadísticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Técnicas no Paramétricas y de Computación Intensiva en Estadísticaes
dc.contributor.authorElías Fernández, Antonio
dc.contributor.authorJiménez Recaredo, Raúl José
dc.contributor.authorShang, Han Lin
dc.date.accessioned2023-06-20T09:58:56Z
dc.date.available2023-06-20T09:58:56Z
dc.date.issued2021-11-01
dc.description.abstractTwo nonparametric methods are presented for forecasting functional time series (FTS). The FTS we observe is a curve at a discrete-time point. We address both one-step-ahead forecasting and dynamic updating. Dynamic updating is a forward prediction of the unobserved segment of the most recent curve. Among the two proposed methods, the first one is a straightforward adaptation to FTS of the k-nearest neighbors methods for univariate time series forecasting. The second one is based on a selection of curves, termed the curve envelope, that aims to be representative in shape and magnitude of the most recent functional observation, either a whole curve or the observed part of a partially observed curve. In a similar fashion to k-nearest neighbors and other projection methods successfully used for time series forecasting, we "project" the k-nearest neighbors and the curves in the envelope for forecasting. In doing so, we keep track of the next period evolution of the curves. The methods are applied to simulated data, daily electricity demand, and NOx emissions and provide competitive results with and often superior to several benchmark predictions. The approach offers a model-free alternative to statistical methods based on FTS modeling to study the cyclic or seasonal behavior of many FTS.en
dc.description.sponsorshipThe authors acknowledge insightful comments and suggestions from two reviewers and the Associate Editor. Antonio Elías is supported by the Spanish Ministerio de Educación, Cultura y Deporte under grant FPU15/00625 and the research stay grant EST17/00841. Antonio Elías and Raúl Jiménez are partially supported by the Spanish Ministerio de Economía y Competitividad under grant ECO2015-66593-P and PID2019-109196GB-I00/AEI/10.13039/501100011033. Funding for open access charge: Universidad de Málaga / CBUA. Part of this article was conducted during a stay at Australian National University. Antonio Elías is grateful to Han Lin Shang for his hospitality and insightful and constructive discussions.en
dc.format.extent13es
dc.identifier.bibliographicCitationElías, A., Jiménez, R., & Shang, H. L. (2021). On projection methods for functional time series forecasting. Journal of Multivariate Analysis, 189, 104890.en
dc.identifier.doihttps://doi.org/10.1016/j.jmva.2021.104890
dc.identifier.issn0047-259X
dc.identifier.publicationfirstpage1es
dc.identifier.publicationissue104890es
dc.identifier.publicationlastpage13es
dc.identifier.publicationtitleJournal of Multivariate Analysisen
dc.identifier.publicationvolume189es
dc.identifier.urihttps://hdl.handle.net/10016/37537
dc.identifier.uxxiAR/0000028861
dc.language.isoengen
dc.publisherElsevieren
dc.relation.projectIDGobierno de España. ECO2015-66593-Pes
dc.relation.projectIDGobierno de España. PID2019-109196GB-I00es
dc.relation.projectIDGobierno de España. FPU15/00625es
dc.relation.projectIDGobierno de España. EST17/00841es
dc.rights© 2021 The Author(s).en
dc.rightsAtribución 3.0 España*
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/*
dc.subject.ecienciaEstadísticaes
dc.subject.otherForecastingen
dc.subject.otherFunctional depthen
dc.subject.otherFunctional nonparametricen
dc.subject.otherFunctional time seriesen
dc.subject.otherNearest neighborsen
dc.titleOn projection methods for functional time series forecastingen
dc.typeresearch article*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
projection_JMA_2022.pdf
Size:
2.13 MB
Format:
Adobe Portable Document Format
Download
Collections
DES - Artículos de Revistas