A classification method for binary predictors combining similarity measures and mixture models
Résumé
In this paper, a new supervised classification method dedicated to binary data is proposed. Its originality is to combine a model-based classification rule with similarity measures thanks to the introduction of new family of exponential kernels. Some links are established between existing similarity measures when they are applied to binary data. A new family of measures is also introduced to unify some of the existing literature. The performance of the new classification method is illustrated on two real datasets (verbal autopsy data and hand-digit data) using 76 similarity measures.
Domaines
Statistiques [math.ST]
Origine : Fichiers produits par l'(les) auteur(s)