New Bootstrap Applications in Supervised Learning

Abstract

Some bootstrap and boosting methods for problems related to classification are introduced in this article. The first method chooses better boosting weights by using a bootstrap search algorithm. The second method is a good way to define a classification frontier. A new formulation for boosting in linear discriminant analysis is given. Since in this new formulation the uncertainty is represented by the weighted covariance matrix, it is more appropriate from the conceptual point of view. Simulation results show that the proposed methods perform well in data analysis.

Keywords:

• Boosting
• Bootstrap
• Bumping

Mathematics Subject Classification:

• 62xx
• 62H30

Acknowledgments

The authors acknowledge support of the Brazilian agency FACEPE (APQ-0461-1.02/06). The authors also thank an anonymous referee, Andrew T. A. Wood (University of Nottingham), and Isaac M. Xavier Junior.