Pub. date: 2009 | Online Pub. Date: October 05, 2009 | DOI: 10.4135/9780857020994 | Print ISBN: 9781412930918 | Online ISBN: 9780857020994| Publisher:SAGE Publications LtdAbout this handbook
Chapter 10: Multidimensional Scaling
Yoshio Takane & Sunho Jung & Yuriko Oshima-Takane
Multidimensional scaling The notion of similarity plays a fundamental role in psychology, especially in cognitive psychology. According to Tversky (1977), similarity is an organizing principle by which we categorize, generalize, and classify objects. These activities are crucial for the survival of species. Multidimensional scaling (MDS) is a collection of data analysis techniques for analysis of proximity data. The word ‘proximity’ here refers to the degree of similarity or dissimilarity among stimuli (objects) of interest. (We use the word ‘proximity’ as a superordinate term that includes both similarity and dissimilarity.) More specifically, MDS is a class of data analysis techniques that represents a set of stimuli as points in a multidimensional space in such a way that the distances between them best represent the observed proximity data between the stimuli. To illustrate, let us look at Figure 10.1A . This is the Greek letter φ. Ten points on this letter were ...