Improving SSA predictions by inverse distance weighting

This paper proposes a method of utilizing spatial information to improve predictions in one dimensional time series analysis using singular spectrum analysis (SSA). It employs inverse distance weighting for spatial averaging and subsequently multivariate singular spectrum analysis (MSSA) for enhance...

Full description

Saved in:
Bibliographic Details
Published inRevstat Vol. 11; no. 1; p. 105
Main Authors Awichi, Richard O, Muller, Werner G
Format Journal Article
LanguageEnglish
Published Instituto Nacional de Estatistica 01.03.2013
Instituto Nacional de Estatística | Statistics Portugal
Subjects
Functions, Inverse
inverse distance weighting
Mathematical research
Prediction (Logic)
singular spectrum analysis
spatio-temporal predictions
Time-series analysis
Online AccessGet full text
ISSN1645-6726
2183-0371
DOI10.57805/revstat.v11i1.129

Cover

More Information
Summary:This paper proposes a method of utilizing spatial information to improve predictions in one dimensional time series analysis using singular spectrum analysis (SSA). It employs inverse distance weighting for spatial averaging and subsequently multivariate singular spectrum analysis (MSSA) for enhanced forecasts. The technique is exemplified on a data set for rainfall recordings from Upper Austria. Key-Words: * singular spectrum analysis; inverse distance weighting; spatio-temporal predictions. AMS Subject Classification: * 49A05, 78B26.
ISSN:1645-6726
2183-0371
DOI:10.57805/revstat.v11i1.129