Summary
In this paper a new algorithmic approach via an eigenvector iteration to fit l p -distances to given dissimilarities with respect to the weighted least squares loss function (Stress) is presented. The optimization problem is cast in the general setting of maximizing a nondifferentiable convex function over the level set of another convex function. Necessary conditions are shown to exhibit a nonlinear eigenproblem, which is approached by a new eigenvector iteration process. Global convergence properties of this algorithm for 1 ≤ p ≤ 2 are established and a psychometric application is given.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
ARABIE, P. (1991): Was Euclid an unnecessarily sophisticated psychologist? Psychometrika56, 567–587.
ATTNEAVE, F. (1950): Dimensions of similarity. Amer. J. Psychol.63, 516–556.
FICHET, B. (1988): L p spaces in data analysis. In: H.H. Bock (ed.): Classification and related methods of data analysis, North-Holland, Amsterdam, 439–444.
GREGSON, R.A.M. (1965): Representation of taste mixture cross-modal-matching in a Minkowski-r-metric. Australian Journal of Psychology17, 3, 195–204.
GROENEN, P.J.F., MATHAR, R., HEISER, W.J. (1993): The majorization approach to multidimensional scaling for Minkowski distances. Journal of Classification, submitted.
HEISER, W.J. (1989): The city-block model for three-way multidimensional scaling. In: R. Coppi, S. Bolasco (eds.): Multivariate data analysis, North-Holland, Amsterdam, 395–404.
HUBERT, L., ARABIE, P., HESSON-MCINNIS, M. (1992): Multidimensional scaling in the city-block metric: a combinatorial approach. Journal of Classification 9, 211–236.
KRUSKAL, J.B. (1964): Nonmetric multidimensional scaling: a numerical method. Psy-chometrika 29, 115–130.
KRUSKAL, J.B., YOUNG, F.W., SEERY, J.B. (1977): How to use KYST-2, a flexible program to do MDS and unfolding. Murray Hill, N.J., AT&T Bell Labs.
MATHAR, R., MEYER, R. (1993): Algorithms in convex analysis to fit l p-distance matrices. Journal of Multivariate Analysis, submitted.
MEULMAN, J.J. (1986): A distance approach to nonlinear multivariate analysis. Leiden, DSWO Press.
MEYER, R. (1991a): Multidimensional scaling as a framework for correspondence analysis and its extensions. In: M. Schader (ed.): Analyzing and modeling data and knowledge, Springer, Berlin, 99–108.
MEYER, R. (1991b): Canonical correlation analysis as a starting point for extensions of correspondence analysis. Statistique et Analyse des Données16, 1, 55–77.
OSBORNE, M.R. (1975): Some special nonlinear least squares problems. SIAM J. Numer. Anal.12, 571–592.
PARLETT, B.N. (1980): The symmetric eigenvalue problem. Prentice Hall, E.C.
RESTLE, F. (1959): A metric and an ordering on sets. Psychometrika 24, 207–220.
ROBERT, F. (1967): Calcul du rapport maximal de deux normes sur IRn . R.I.R.O.5, 97–118.
ROCKAFELLAR, R.T. (1970): Convex analysis. Princeton University Press, Princeton.
ROSKAM, E.E. (1981): Data theory and scaling: a methodological essay on the role and use of data theory and scaling in psychology. In: I. BORG (ed.): Multidimensional data representations: when and why, Mathesis Press, Ann Arbor, Michigan.
SHEPARD, R.N. (1964): Attention and the metric structure of the stimulus space. Journal of Math. Psychology 1, 54–87.
TVERSKY, A., KRANTZ, D.H. (1970): The dimensional representation and the metric structure of similarity data. J. Math. Psychology 7, 572–596.
WATSON, G.A. (1985): On a class of algorithms for total approximation. Journal of Approximation Theory 45, 219–231.
WILKINSON, L. (1988): SYSTAT: The system for statistics. Evanston, IL, SYSTAT, Inc.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Meyer, R. (1994). An Eigenvector Algorithm to Fit l p -Distance Matrices. In: Diday, E., Lechevallier, Y., Schader, M., Bertrand, P., Burtschy, B. (eds) New Approaches in Classification and Data Analysis. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-51175-2_58
Download citation
DOI: https://doi.org/10.1007/978-3-642-51175-2_58
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58425-4
Online ISBN: 978-3-642-51175-2
eBook Packages: Springer Book Archive