000186501 001__ 186501
000186501 005__ 20190316235631.0
000186501 0247_ $$2doi$$a10.1016/j.apm.2012.09.040
000186501 022__ $$a0307-904X
000186501 02470 $$2ISI$$a000316579600008
000186501 037__ $$aARTICLE
000186501 245__ $$aSpectral modeling of time series with missing data
000186501 260__ $$aNew York$$bElsevier$$c2013
000186501 269__ $$a2013
000186501 300__ $$a9
000186501 336__ $$aJournal Articles
000186501 520__ $$aSingular spectrum analysis is a natural generalization of principal component methods for time series data. In this paper we propose an imputation method to be used with singular spectrum-based techniques which is based on a weighted combination of the forecasts and hindcasts yield by the recurrent forecast method. Despite its ease of implementation, the obtained results suggest an overall good fit of our method, being able to yield a similar adjustment ability in comparison with the alternative method, according to some measures of predictive performance. (C) 2012 Elsevier Inc. All rights reserved.
000186501 6531_ $$aKarhunen-Loeve decomposition
000186501 6531_ $$aMissing data
000186501 6531_ $$aSingular spectrum analysis
000186501 6531_ $$aTime series analysis
000186501 700__ $$aRodrigues, Paulo C.$$uNova Univ Lisbon, Ctr Math & Applicat, Fac Sci & Technol, P-2829516 Caparica, Portugal
000186501 700__ $$0245140$$aDe Carvalho, Miguel$$g206788
000186501 773__ $$j37$$k7$$q4676-4684$$tApplied Mathematical Modelling
000186501 8564_ $$s459486$$uhttps://infoscience.epfl.ch/record/186501/files/paper.pdf$$yPreprint$$zPreprint
000186501 909C0 $$0252136$$pSTAT$$xU10124
000186501 909CO $$ooai:infoscience.tind.io:186501$$pSB$$particle$$qGLOBAL_SET
000186501 917Z8 $$x111184
000186501 937__ $$aEPFL-ARTICLE-186501
000186501 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000186501 980__ $$aARTICLE