Multidimensional Scaling (From Blockmodel Techniques for Criminal Justice Research - Final Report, Appendix D, 1981, by Phipps Arabie See NCJ-88432)

• NCJ Number: 88435
• Author(s): J D Carroll; P Arabie
• Date Published: 1981
• Length: 44 pages
• Grant Number(s): 78-NI-AX-0142; SOC 76-24394; SOC 76-24512
• Sponsoring Agency: National Science Foundation; National Institute of Justice (NIJ); US Dept of Justice NIJ Pub
• Publication Format: Article
• Publication Type: Report (Study/Research)
• Language: English
• Country: United States of America
• Note: Reprinted from Ann. Rev. Psychol 1980 31:607-49

Annotation

Multidimensional scaling (MDS) comprises a family of geometric models for multidimensional representation of data and a corresponding set of methods for fitting such models to actual data. It includes nonspatial and nondistance models that apply to nonproximities data as well as to proximities. This paper imposes a taxonomy on the MDS field.

Abstract

It updates and generalizes Coombs's (1964) 'A Theory of Data.' However, in contrast to Coombs, this paper attempts separate taxonomies of data and of models, whereas Coombs argued that data cannot be classified independently of the model to which those data are referred. The discussion covers one-mode two-way data, two-mode two-way data, two-mode three-way data, three-mode three-way data, and higher-way data. It considers data collection and related issues, new areas of usage for MDS, and textbook aids to users. Equations and about 490 references are included.