Component extraction analysis of multivariate time series

Akman I., DeGooijer J.

COMPUTATIONAL STATISTICS & DATA ANALYSIS, cilt.21, sa.5, ss.487-499, 1996 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 21 Sayı: 5
  • Basım Tarihi: 1996
  • Doi Numarası: 10.1016/0167-9473(95)00031-3
  • Dergi Adı: COMPUTATIONAL STATISTICS & DATA ANALYSIS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.487-499
  • Orta Doğu Teknik Üniversitesi Adresli: Hayır

Özet

A method for modelling several observed parallel time series is proposed. The method involves seeking possible common underlying pure AR and MA components in the series. The common components are forced to be mutually uncorrelated so that univariate time series modelling and forecasting techniques can be applied. The proposed method is shown to be a useful addition to the time series analyst's toolkit, if common sources of variation in multivariate data need to be quickly identified.