Velilla Cerdan, SantiagoHernández, Adolfo2006-11-092006-11-092001-11https://hdl.handle.net/10016/176Dimension reduction transformations in discriminant analysis are introduced. Their properties, as well as sufficient conditions for their characterization, are studied. Special attention is given to the continuous case, of particular importance in applications. An effective data based dimension reduction algorithm is proposed and its behavior illustrated in a classification problem where the class conditional probability distributions are multivariate normal with different covariance matrices517344 bytesapplication/pdfengworking paperEstadísticaopen accessws016614