Möbus, Claus (1976) Nonmetric Multidimensional Scaling without Disparities and Derivatives: A Rankcorrelation-Orientated Approach Through L1-Approximation. Archiv für Psychologie, 128. pp. 240-266. ISSN 0066-6475

Preview

- Published Version Volltext (4Mb)

Abstract

A new nonmetric multidimensional scaling method is presented. The method is transformation-free (no monotonic transformation of data) and operates directly on distances and data rankorders. Numeric examples demonstrate that our method is not inferior to the classical nonmetric alternatives. An analysis of Lingoes & Roskam's (1973) order-4 matrices generated results with a still improved rank-order isomorphy.

Item Type:	Article
Uncontrolled Keywords:	nonmetric multidimensional scaling, transformation-free, order-4 matrices, rank-order isomorphy
Subjects:	Generalities, computers, information > Computer science, internet Philosophy and psychology > Psychology
Divisions:	School of Computing Science, Business Administration, Economics and Law > Department of Computing Science
Date Deposited:	22 Jan 2016 08:38
Last Modified:	22 Jan 2016 08:38
URI:	https://oops.uni-oldenburg.de/id/eprint/2621
URN:	urn:nbn:de:gbv:715-oops-27022
DOI:
Nutzungslizenz:

Actions (login required)

View Item