A new method of discrimination on qualitative variables : Categorical multiblock linear discriminant analysis

The aim of this paper is to propose a new method of discrimination when the dependant variable is categorical and when a large number of categorical explanatory variables is retained. This method, Categorical Multiblock Linear Discriminant Analysis (CMLDA), computes components which take into account both relationships between explanatory categorical variables and canonical correlation between each explanatory categorical variable and the dependant variable. A comparison with two other techniques and an application on credit scoring data are provided.