Multivariate correlation analysis - a method for the analysis of multidimensional time series in environmental studies

Abstract After a short demonstration of the theoretical base of univariate, partial and multiple correlation analysis (auto- and cross-correlation), the multivariate auto- and crosscorrelation function was deduced. One advantage of multivariate correlation is the possibility for simultaneous handling of all variables of the time or local series, which allows considering all interactions within the variables in the series and between the series which are dependent upon lag. Applications in environmental analysis are provided in this text for the partial crosscorrelation and the multivariate auto- and crosscorrelation for three selected practical examples.