K-means clustering in a low-dimensional Euclidean space

A procedure is developed for clustering objects in a low-dimensional subspace of the column space of an objects by variables data matrix. The method is based on the K-means criterion and seeks the subspace that is maximally informative about the clustering structure in the data. In this low-dimensional representation, the objects, the variables and the cluster centroids are displayed jointly. The advantages of the new method are discussed, an efficient alternating least-squares algorithm is described, and the procedure is illustrated on some artificial data.

[1]  G. Young.  Maximum likelihood estimation and factor analysis , 1941 .

[2]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[3]  K. Gabriel,et al.  The biplot graphic display of matrices with application to principal component analysis , 1971 .

[4]  R. Ferber.  Handbook of Marketing Research , 1974 .

[5]  G. W. Milligan,et al.  An examination of the effect of six types of error perturbation on fifteen clustering algorithms , 1980 .

[6]  Wei-Chien Chang.  On using Principal Components before Separating a Mixture of Two Multivariate Normal Distributions , 1983 .

[7]  Girish N. Punj,et al.  A Typology of Individual Search Strategies Among Purchasers of New Automobiles , 1984 .

[8]  John Saunders,et al.  Market Segmentation and Positioning in Specialized Industrial Markets , 1985 .

[9]  W. Heiser,et al.  Clusteringn objects intok groups under optimal scaling of variables , 1989 .

[10]  W. DeSarbo,et al.  Multiclus: A new method for simultaneously performing multidimensional scaling and cluster analysis , 1991 .

[11]  W. DeSarbo,et al.  Simultaneous multidimensional unfolding and cluster analysis: An investigation of strategic groups , 1991 .

[12]  Willem J. Heiser,et al.  Clustering in Low-Dimensional Space , 1993 .

[13]  Suzanne Winsberg,et al.  A latent class vector model for preference ratings , 1993 .

[14]  W. Heiser,et al.  A latent class unfolding model for analyzing single stimulus preference ratings , 1993 .

[15]  Otto Opitz,et al.  Information and Classification , 1993 .

[16]  Suzanne Winsberg,et al.  A latent class approach to fitting the weighted Euclidean model, clascal , 1993 .