[en] We describe for two groups a stepwise selection method of the most discriminant parameters, based on the logistic rule and the e632 error rate estimator in discriminant analysis. This stepwise discriminant method can be used as an alternative method in non-normality or heteroscedasticity situations, where the stepwise linear discriminant analysis is not suitable. The implementation of this stepwise method on Isoberlinia woodland and tree savannah identifies the most discriminant parameters as the global dominant height, the dominant height of Isoberlinia trees and the number of species per hectare. For these parameters, the value of the error rate associated with the logistic rule and estimated by th e632 estimators is 24,6 %.
