Standard Article

Multidimensional Scaling

  1. Geert De Soete1,
  2. J. Douglas Carroll2

Published Online: 15 JUL 2005

DOI: 10.1002/0470011815.b2a13041

Encyclopedia of Biostatistics

Encyclopedia of Biostatistics

How to Cite

De Soete, G. and Carroll, J. D. 2005. Multidimensional Scaling. Encyclopedia of Biostatistics. 5.

Author Information

  1. 1

    University of Ghent, Ghent, Belgium

  2. 2

    Rutgers University, Piscataway, NJ, USA

Publication History

  1. Published Online: 15 JUL 2005


Multidimensional scaling includes a set of models and associated methods for constructing geometrical representations of proximity or dominance relationships between elements in one or more sets of entities. The most common techniques of multidimensional scaling are described and illustrated.


  • co-occurrence data;
  • confusion;
  • transition frequencies;
  • second-order proximities;
  • Euclidean space;
  • target distances;
  • optimally scaled data;
  • goodness of fit;
  • loss function;
  • dominance;
  • unfolding model;
  • ideal point model;
  • common space;
  • object space;
  • source space;
  • private space' INDSCAL model