Akaike's information criterion is suggested as a tool for evaluating fit and dimensionality in metric multidimensional scaling that uses least squares methods of estimation. This criterion combines the least squares loss function with the number of estimated parameters. Numerical examples are presented. The results from analyses of both simulation…

Data generated by the pair-comparison method can be analyzed by least squares. A system of normal equations is derived by which the original objects are scaled. One advantage of this method is that it is not necessary to compare all object pairs. Examples are provided. (Author/JKS)

A reanalysis of the intercorrelation matrix from a principal components analysis of the Life Styles Inventory was conducted using a Canadian sample. Using nonmetric multidimensional scaling, analyses show an almost perfect circumplex pattern. Results illustrate the inadequacy of factor analytic procedures for the analysis and representation of a…