Discriminant Analysis on Mixed Predictors

The processing of mixed data both quantitative and qualitative variables - cannot be carried out as explanatory variables through a discriminant analysis method. In this work, we describe a methodology of a discriminant analysis on mixed predictors. The proposed method uses simultaneously quantitative and qualitative explanatory data with a discrimination and classification aim. It's a classical discriminant analysis carried out on the principal factors of a Mixed Principal Component Analysis of explanatory mixed variables, i.e. both quantitative and transformed qualitative variables associate to the dummy variables. An example resulting from real data illustrates the results obtained with this method, which are also compared with those of a logistic regression model.