A generalized majorization method for least squares multidimensional scaling of pseudodistances that may be negative

DOI10.1007/BF02294582zbMath0726.92032MaRDI QIDQ803090

Willem J. Heiser

Publication date: 1991

Published in: Psychometrika (Search for Journal in Brave)

zbMATH Keywords

monotone convergencemetric multidimensional scalingadditive constantrobust fittingcity-block distance modelleast absolute residualsleast squares multidimensional scalingnegative pseudodistancesSMACOF algorithm

Mathematics Subject Classification ID

One- and multidimensional scaling in the social and behavioral sciences (91C15) Numerical methods for mathematical programming, optimization and variational techniques (65K99)

Related Items

Cluster differences unfolding for two-way two-mode preference rating data, A latent class unfolding model for analyzing single stimulus preference ratings, The majorization approach to multidimensional scaling for Minkowski distances, Triadic distance models: axiomatization and least squares representation, Radial basis functions for exploratory data analysis: An iterative majorisation approach for Minkowski distances based on multidimensional scaling, The Gifi system of descriptive multivariate analysis., The tunneling method for global optimization in multidimensional scaling, A dual latent class unfolding model for two-way two-mode preference rating data

Uses Software

• KYST

Cites Work

• Unnamed Item
• Unnamed Item
• Correspondence analysis with least absolute residuals
• Convergence of the majorization method for multidimensional scaling
• A general nonmetric technique for finding the smallest coordinate space for a configuration of points
• A new solution to the additive constant problem in metric multidimensional scaling
• Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis
• Nonmetric multidimensional scaling. A numerical method