New Ideas for Sufficient Dimension Reduction for Functional Data

• Activity Number: 144
• Type: Contributed
• Date/Time: Monday, August 5, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): James Wright*+
• Keywords: functional data ; dimension reduction ; support vector machine

Abstract

In this work we present some new ideas for performing sucient dimension reduction in functional data. We use the ideas of inverse regression and support vector machines to achieve this. We will discuss two methods which both treat the functional data as multivariate data. The rst method to be presented expand the ideas of Li, Artemiou and Li (2011) which were introduced for multivariate data to include functional data. In the second method being discussed the ideas of Li and Yu (2008) are used. Both algorithms show promising results.