Multidimensional scaling (MDS) is a statistical technique often used in and data visualisation. It is a procedure for producing a lower-dimensional data suitable for graphing or 3D visualisation from a high-dimensional data set, whilst preserving some of the most prominent "distance" relationships of the high-dimensional data set.

Applications include scientific visualisation and data mining in fields such as cognitive science, psychophysics and psychometrics. The technique is also used in marketing.

References:

• Kruskal, J. B., and Wish, M. (1978), Multidimensional Scaling, Sage University Paper series on Quantitative Application in the Social Sciences, 07-011. Beverly Hills and London: Sage Publications.

See also:

• Multidimensional scaling (in marketing)

External links

• An elementary introduction to multidimensional scaling (http://www.mathpsyc.uni-bonn.de/doc/delbeke/delbeke.htm)
• Evaluation of multidimensional scaling algorithms (http://www.pavis.org/essay/multidimensional_scaling.html)