Detection and Characterization of Changes of Correlation Structure
in Multivariate Time Series

Markus Müller

Facultad de Ciencias
Universidad Autónoma del Estado de Morelos, México

Freitag, 25.06.2004, 11 Uhr c.t., M7-114
We propose a method based on the equal-time correlation matrix as a sensitive detector for phase-shape correlations in multivariate data sets. The key point of the method is that changes of the degree of synchronization between time series provoke level repulsions between eigenstates at both edges of the spectrum of the correlation matrix.

Consequently, detailed information about the correlation structure of the multivariate data set is imprinted into the dynamics of the eigenvalues and into the structure of the corresponding eigenvectors.

The performance of the technique is demonstrated by application to articicially created datasets and electroencephalographic recordings of eplileptic patients with the aim to detect and characterizea possible precursor activity. A comparison with the Independent Component Analysis is provided. The high sensitivity and the comparatively small computational effort recommend it for application to the analysis of complex, spatially extended, nonstationary systems.


sfb-logo Zur Startseite Erstellt von: Anke Weinberger (2004-06-02).
Wartung durch: Anke Weinberger (2004-06-21).