Distance-Based Measures of Association with Applications in Relating Hyperspectral Images

Abstract

We propose a distance-based method to relate two data sets. We define and study some measures of multivariate association based on distances between observations. The proposed approach can be used to deal with general data sets (e.g., observations on continuous, categorical or mixed variables). An application, using Hellinger distance, provides the relationships between two regions of hyperspectral images.

Keywords:

• Binary partition tree
• Canonical correlations
• Hellinger distance
• Metric multidimensional scaling
• Wilks lambda

Mathematics Subject Classification:

• Primary 62H20
• Secondary 62H35

Acknowledgments

Work supported in part by MEC (Spain) grant MTM2008-00642. Thanks are due to two anonymous referees for useful comments.