Some Statistical Approaches to Multidimensional Scaling Data

摘要: Statistical problems associated with multidimensional scaling are reviewed. Indices of similarity or dissimilarity have been fitted by two classes models: point representation using a distance measure and vector an inner product. In addition to these parameters representing stimulus-attribute relations, it is usual require some subject-specific model idiosyncracies in response patterns variance components. Techniques for coping nuisance deriving interval estimates discussed the context maximum likelihood estimation. Some generalizations multivariate situations also developed.