| Abstract: | Environmental data are highly variable. They also include uncertainties resulting from all steps of the analytical process e. g. sampling, or sampling pre‐treatment. However, a lot of information is unfortunately often lost because only univariate statistical methods are used for data evaluation and interpretation. This neglects correlation between different pollutants and relationships among various sampling points. It is therefore necessary to apply additional methods of analysis that can accommodate such relationships. This ability is provided by the established, and by the more modern, multivariate statistical methods because they can analyze complex sets of multidimensional data. These methods are used to visualize large amounts of data and to extract latent information (e. g. differently polluted areas, dischargers, or interactions between different environmental compartments). The goal of this paper is to present the use of established statistical techniques, like cluster or factor analysis, and the progress made in basic modern techniques (e. g. cluster imaging, multiway‐partial least squares regression, projection pursuit, or information theory) and to demonstrate each with examples and illustrations. |
