Correlation between soil characters and forest types: a study in multiple discriminant analysis

Multiple discriminant analysis is a useful multivariate technique in vegetation studies that can be employed for several purposes, even if the underlying statistical assumptions are not satisfied. An example of application of this method is discussed: multiple discriminant analysis was successfully used for evaluating the predictivity of forest types defined by numerical classification of vegetation data with respect to soil variables.Species nomenclature follows Pignatti (1982) for vascular plants and Augier (1966) for mosses.The research has been supported by the IDROSER (Bologna, Italy) and by the Italian C. N. R. (Grant no. 83.02548.04, resp. Prof. A. Pirola). We wish to thank Prof. E. Feoli, Prof. E. van der Maarel, Prof. L. Orlóci and Prof. A. Pirola for suggestions. We are also indebted to Dr N. Filippi who analyzed the soil samples.