Abstract
A new approach to discriminant analysis based on projection pursuit density estimation is proposed. Projections are chosen to minimize estimates of the expected overall loss in each projection pursuit stage. Different strategies in the procedure concerning the choice of univariate density estimates and bandwidths used to estimate the function of interest in the minimization step, to fix the direction α and to update the discriminant rule and the estimates of the densities are discussed. Cross-validation techniques are used to avoid overfitting effects. In a simulation study several variants of the procedure are compared with discriminant rules based on normality assumptions and nonparametric classification procedures.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
