Correspondence analysis as a tool in fungal taxonomy

The polyphasic approach to taxonomic problems has led to the creation of complex datasets that lend themselves to numerical analysis. The numerical study, however, has to deal with mathematical problems linked with the presence of mixed-type data originating from the investigations. Correspondence analysis (CA) is an ordination technique widely used in ecology and social sciences but only rarely applied to taxonomic problems. In CA corresponding variables and taxa ordination are obtained simultaneously, thus allowing to explore the taxonomic interrelationships between taxa and variables in a single analysis. CA can be used on large and small datasets, and can be applied to mixed-type data after appropriate coding. It is not sensitive to variation of class number and size and is useful to screen large unstructured datasets, to suggest which variables should be retained to discriminate samples, to detect outliers or erroneous data and to perform identification of unknown samples. It also has the advantage of handling missing data particularly well. On the other hand, CA is sensitive to outliers, which can cause a distortion of the geometric map of the points in the graphical display. Nevertheless, the sensitivity of correspondence analysis to outliers can be effectively used to verify data. Finally, based on symmetry of row and column analyses correspondence analysis can be applied to find out which characters can be used to construct identification keys and to selectively group variables by their importance for the discrimination of samples.