DISTATIS: The Analysis of Multiple Distance Matrices

Authors:
Herve Abdi;Alice J. O'Toole;Dominique Valentin;Betty Edelman
Affiliations:
The University of Texas at Dallas;The University of Texas at Dallas;Universite de Bourgogne;The University of Texas at Dallas
Venue:
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Year:
2005

Citing 0
Cited 3

Manifold integration with Markov random walks

AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 1
GeneTerrain: visual exploration of differential gene expression profiles organized in native biomolecular interaction networks

Information Visualization
An ExPosition of multivariate analysis with the singular value decomposition in R

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a generalization of classical multidimensional scaling called DISTATIS which is a new method that can be used to compare algorithms when their outputs consist of distance matrices computed on the same set of objects. The method first evaluates the similarity between algorithms using a coefficient called the RV coefficient.From this analysis, a compromise matrix is computed which represents the best aggregate of the original matrices. In order to evaluate the differences between algorithms, the original distance matrices are then projected onto the compromise. We illustrate this method with a "toy example" in which four different "algorithms" (two computer programs and two sets of human observers) evaluate the similarity among faces.