ABSTRACT
MULTIDIMENSIONAL SCALING is useful because a picture is often easier to interpret than a table of numbers. In multidimensional scaling, a matrix made up of dissimilarity data (for example, ratings of how different products are, or distances between cities) is converted into a one-, two-, or three-dimensional graphical representation of those distances. Although it is possible to have more than three dimensions in multidimensional scaling, that is rather rare.
