, Volume 41, Issue 4, pp 439–463 | Cite as

Spatial, non-spatial and hybrid models for scaling

  • J. Douglas Carroll


In this paper, hierarchical and non-hierarchical tree structures are proposed as models of similarity data. Trees are viewed as intermediate between multidimensional scaling and simple clustering. Procedures are discussed for fitting both types of trees to data. The concept of multiple tree structures shows great promise for analyzing more complex data. Hybrid models in which multiple trees and other discrete structures are combined with continuous dimensions are discussed. Examples of the use of multiple tree structures and hybrid models are given. Extensions to the analysis of individual differences are suggested.

Key words

multidimensional scaling hierarchical tree structures clustering geometric models multivariate data analysis 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Reference notes

  1. Carroll, J. D., and Pruzansky, S. Fitting of hierarchical tree structure (HTS) models, mixtures of HTS models, and hybrid models, via mathematical programming and alternating least squares. Presented at theU.S.-Japan Seminar on Theory, Methods, and Applications of Multidimensional Scaling and related techniques, San Diego, Aug. 1975. Paper in informally published Proceedings of U.S.-Japan Seminar, available on request.Google Scholar
  2. Cunningham, J. P. On finding an optimal tree realization of a proximity matrix. Paper presented at the Mathematical Psychology meeting, Ann Arbor, Michigan, August 29, 1974.Google Scholar
  3. Harshman, R. A. PARAFAC2: Mathematical and technical notes (Working Papers in Phonetics No. 22). Los Angeles: University of California, March, 1972.Google Scholar
  4. Kruskal, Joseph B. Some advances in parametric mapping. Psychometric Society Presidential Address, presented at joint meeting of Psychometric Society and Classification Society, Iowa City, Iowa, April, 1975.Google Scholar
  5. Sattath, S. and Tversky, A. Additive similarity trees. Unpublished manuscript, Hebrew University, 1976.Google Scholar
  6. Shepard, R. N. and Arabie, P. Additive cluster analysis of similarity data. Paper presented at the U.S.-Japan Seminar on Theory, Methods, and Applications of Multidimensional Scaling and Related Techniques, San Diego, 1975. Paper in informally published Proceedings of U.S.-Japan Seminar.Google Scholar
  7. Tversky, A. Features of similarity. Unpublished manuscript, Hebrew University, Jerusalem, Israel, 1976.Google Scholar


  1. Buneman, P. The recovery of trees from measures of dissimilarity. In F. R. Hodson' D. G. Kendall and P. Tautu (Eds.),Mathematics in the archaeological and histroical sciences. Edinburgh: Edinburgh University Press, 1971, 387–395.Google Scholar
  2. Carroll, J. D., and Chang, J. J. Analysis of individual differences in multidimensional scaling via an N-way generalization of “Eckart-Young” decomposition.Psychometrika, 1970,35, 283–319.Google Scholar
  3. Carroll, J. D. and Chang, J. J. A method for fitting a class of hierarchical tree structure models to dissimilarities data and its application to some “body parts” data of Miller's.Proceedings of the 81st Annual Convention of the American Psychological Association, 1973,8, 1097–1098.Google Scholar
  4. Degerman, R. Multidimensional analysis of complex structure: Mixtures of class and quantitative variation.Psychometrika, 1970,35, 475–491.CrossRefGoogle Scholar
  5. de Leeuw, J., Young, F. W. and Takane, Y. Additive structure in qualitative data: An alternating least squares method with optimal scaling features.Psychometrika, 1976, 000-000.Google Scholar
  6. Dobson, J. Unrooted trees for numerical taxonomy.Journal of Applied Probability, 1974,11, 32–42.Google Scholar
  7. Hartigan, J. A. Representation of similarity matrices by trees.Journal of the American Statistical Association, 1967,62, 1140–1158.Google Scholar
  8. Holman, E. W. The relation between hierarchical and Euclidean models for psychological distances.Psychometrika, 1972,37, 417–423.CrossRefGoogle Scholar
  9. Horan, C. B. Multidimensional scaling: Combining observations when individuals have different perceptual structures.Psychometrika, 1960,34, 139–165.Google Scholar
  10. Johnson, S. C. Hierarchical clustering schemes.Psychometrika, 1967,32, 241–254.CrossRefPubMedGoogle Scholar
  11. Miller, G. A. A psychological method to investigate verbal concepts.Journal of Mathematical Psychology, 1969,6, 169–191.CrossRefGoogle Scholar
  12. Patrinos, A. N. and Hakimi, S. L. The distance matrix of a graph and its tree realization.Quarterly of Applied Mathematics, 1972,30, 255–269.Google Scholar
  13. Romney, A. K. and D'Andrade, R. G. Cognitive aspects of English kin terms.American Anthropologist, 1964,66, No. 3, part 2 (special publication), 146–170.Google Scholar
  14. Rosenberg, S. and Kim, M. P. The method of sorting as a data-gathering procedure in multivariate research.Multivariate Behavioral Research, 1975,10, 489–502.CrossRefGoogle Scholar
  15. Shepard, R. N. Representation of structure in similarity data: Problems and prospects.Psychometrika, 1974,39, 373–421.CrossRefGoogle Scholar
  16. Torgerson, W. S. Multidimensional scaling of similarity.Psychometrika, 1965,30, 379–393.CrossRefPubMedGoogle Scholar
  17. Tucker, L. R. Relations between multidimensional scaling and three-mode factor analysis.Psychometrika, 1972,37, 3–27.CrossRefGoogle Scholar
  18. Wish, M., Kaplan, S. J. and Deutsch, M. Dimensions of interpersonal relations: Preliminary results.Proceedings of the 81st Annual Convention of the American Psychological Association, 1973,8, 179–180.Google Scholar
  19. Wish, M. Comparisons among multidimensional structures of interpersonal relations.Multivariate Behavioral Research, in press.Google Scholar
  20. Wold, H. Estimation of principal components and related models by iterative least squares. In P. R. Krishnaiah (Ed.),Multivariate Analysis. New York: Academic Press, 1966.Google Scholar

Copyright information

© Psychometric Society 1976

Authors and Affiliations

  • J. Douglas Carroll
    • 1
  1. 1.Bell LaboratoriesMurray Hill

Personalised recommendations