caa a22 4500 475762568 CHVBK 20180406123555.0 cr unu---uuuuu 170329e20001201xx s 000 0 eng 10.1023/A:1026523632608 doi (NATIONALLICENCE)springer-10.1023/A:1026523632608 Gu¨ss Stefan Institute of Hydrophysics, GKSS Research Centre, Max-Planck-Strasse 1, D-21502, Geesthacht, F.R.G aut Cyclo-stationary maximum cross-covariance analysis for exogenously forced environmental systems [Elektronische Daten] [Stefan Gu¨ss] The response of an ecological system to external forcings shows marked seasonality and complex time delays. In order to take seasonality into account, the assumption of stationarity inherent in most statistical models for time series is replaced here by more flexible cyclo-stationarity. To describe the dominant modes of the cross-covariance structure of the system and the forcing, temporal (orthonormal) patterns are derived. They are estimated by a singular value decomposition of the cyclo-stationary sample cross-covariance matrix. These patterns allow to formulate a prediction scheme for the system once the forcing is known. The method has comparatively little tendency for multi-collinearity, so that it is well applicable also for multivariate settings and shorter data records. The method is illustrated for an aquatic ecosystem with distinct phases of a biological succession. Kluwer Academic Publishers, 2000 cyclo-stationary environmental time series nationallicence exogenous predictability nationallicence multiple-input multiple-output system nationallicence seasonality nationallicence singular value decomposition nationallicence state variables nationallicence system analysis nationallicence Environmental and Ecological Statistics Kluwer Academic Publishers 7/4(2000-12-01), 385-404 1352-8505 7:4<385 2000 7 10651 https://doi.org/10.1023/A:1026523632608 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1023/A:1026523632608 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Gu¨ss Stefan Institute of Hydrophysics, GKSS Research Centre, Max-Planck-Strasse 1, D-21502, Geesthacht, F.R.G aut NATIONALLICENCE 773 0- Environmental and Ecological Statistics Kluwer Academic Publishers 7/4(2000-12-01), 385-404 1352-8505 7:4<385 2000 7 10651 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer