Psychometrika

, Volume 47, Issue 1, pp 25–45 | Cite as

A multidimensional scaling model for the size-weight illusion

  • Terrence R. Dunn
  • Richard A. Harshman
Article

Abstract

The kinds of individual differences in perceptions permitted by the weighted euclidean model for multidimensional scaling (e.g., INDSCAL) are much more restricted than those allowed by Tucker's Three-mode Multidimensional Scaling (TMMDS) model or Carroll's Idiosyncratic Scaling (IDIOSCAL) model. Although, in some situations the more general models would seem desirable, investigators have been reluctant to use them because they are subject to transformational indeterminacies which complicate interpretation. In this article, we show how these indeterminacies can be removed by constructing specific models of the phenomenon under investigation. As an example of this approach, a model of the size-weight illusion is developed and applied to data from two experiments, with highly meaningful results. The same data are also analyzed using INDSCAL. Of the two solutions, only the one obtained by using the size-weight model allows examination of individual differences in the strength of the illusion; INDSCAL can not represent such differences. In this sample, however, individual differences in illusion strength turn out to be minor. Hence the INDSCAL solution, while less informative than the size-weight solution, is nonetheless easily interpretable.

Key words

individual differences multidimensional scaling three-mode factor INDSCAL size-weight illusions 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Reference notes

  1. Harshman, R. A. Generalizing INDSCAL and PARAFAC1: Uniqueness of certain representations of three-way crossproduct arrays. Unpublished manuscript, 1981.Google Scholar
  2. Carroll, J. D. & Chang, J. J. IDIOSCAL (individual differences in orientation scaling): A generalization of INDSCAL allowing idiosynchratic reference systems as well as an analytic approximation to INDSCAL. Paper presented at meetings of the Psychometric Society, Princeton, N.J. 1972.Google Scholar
  3. Cohen, H. S. Three-mode rotation to approximate INDSCAL structure. Paper presented at the meetings of the Psychometric Society, Stanford, California, 1974.Google Scholar
  4. Harshman, R. A. Oblique coordinate systems in multidimensional scaling: Theory and experimental test. Unpublished manuscript, May 1973.Google Scholar

References

  1. Anderson, N. H. Averaging model applied to the size-weight illusion.Perception and Psychophysics, 1970,8, 1–4.Google Scholar
  2. Birnbaum, M. H. & Veit, C. T. Scale free tests of an additive model for the size-weight illusion.Perception and Psychophysics, 1974,16, 276–282.Google Scholar
  3. Bloxom, B. Individual differences in multidimensional scaling.Research Bulletin 68-45. Princeton, N.J.: Educational Testing Service, 1968.Google Scholar
  4. Bloxom, B. Constrained multidimensional scaling inN spaces.Psychometrika, 1978,43, 397–408.Google Scholar
  5. Carroll, J. D. & Chang, J. J. Analysis of individual differences in multidimensional scaling via anN-way generalization of “Eckart-Young” decomposition.Psychometrika 1970,35, 282–319.Google Scholar
  6. Carroll, J. D., Pruzansky, S. & Kruskal, J. B. CANDELINC: A general approach to multidimensional analysis of many-way arrays with linear constraints on parameters.Psychometrika, 1980,45, 3–24.Google Scholar
  7. Carroll J. D. & Wish, M. Methods and models for three way multidimensional scaling. In Krantz, D. H. et al. (Eds.)Contemporary developments in mathematical psychology, Volume II. San Francisco: W. H. Freeman, 1974.Google Scholar
  8. Cooper, L. G. A new solution to the additive constant problem in multidimensional scaling.Psychometrika, 1972,37, 311–322.Google Scholar
  9. Donovan, R. J. & Ross, J. The dimensionality of judgments of heaviness.Perception and Psychophysics, 1969,6, 247–249.Google Scholar
  10. Eckart, C. & Young G. The approximation of one matrix by another of lower rank.Psychometrika, 1936,3, 211–218.Google Scholar
  11. Harshman, R. A. Foundations of the PARAFAC procedure: Models and conditions for an “explanatory” multi-model factor analysis. UCLA Working papers in Phonetics16, 1970, 84 pp. [Reprinted by Xerox University Microfilms, Ann Arbor, Mi., Order No. 10,085]Google Scholar
  12. Harshman, R. A. PARAFAC 2: Mathematical and Technical Notes.UCLA Working Papers in Phonetics 22, 1972, 111–117. [Reprinted by Xerox University Microfilms, Ann Arbor, Mi., Order No. 10,085.]Google Scholar
  13. Harshman, R. A. & Berenbaum, S. A. Basic concepts underlying the PARAFAC-CANDECOM three-way factor analysis model and its application to longitudinal data. In Eichorn, D. H., Mussen, P. H., Clausen, J. A., Haan, N., & Honzik, M. P. (Eds.),Present and Past in Middle Life. New York: Academic Press, 1981.Google Scholar
  14. Horan, C. B. Multidimensional scaling combining observations when individuals have different perceptual spaces.Psychometrika, 1969,34, 139–165.Google Scholar
  15. Kruskal, J. B. More factors than subjects, tests, and treatments: An indeterminacy theorem for canonical decomposition and individual differences scaling.Psychometrika, 1976,41, 281–293.Google Scholar
  16. Kruskal, J. B. Three-way arrays: Rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics.Linear Algebra and Its Applications, 1977,18, 95–138.Google Scholar
  17. MacCallum, R. C. Effects on INDSCAL of nonorthogonal perceptions of object space dimension.Psychometrika, 1976,41, 177–188.(a)Google Scholar
  18. MacCallum, R. C. Transformation of a three-mode multidimensional scaling solution to INDSCAL form.Psychometrika, 1976,41, 297–305. (b)Google Scholar
  19. Ramsey, J. O. Maximum likelihood estimation in multidimensional scaling.Psychometrika, 1977,42, 241–266.Google Scholar
  20. Ross, J. A remark on Tucker & Messick's “points of view” analysis.Psychometrika, 1966,31, 27–31.Google Scholar
  21. Ross, J & DiLollo, V. A vector model for psychophysical judgment.Journal of Experimental Psychology, Monograph Supplement, 1968,3, 1–16.Google Scholar
  22. Sarris, V. & Heineken, E. An experimental test of two mathematical models applied to the size-weight illusion.Journal of Experimental Psychology, 1976,2, 295–298.Google Scholar
  23. Sjoberg, L. Sensation scales in the size-weight illusion.Scandinavian Journal of Psychology, 1969,10, 109–112.Google Scholar
  24. Stevens, J. C. & Ruben, L. L. Psychophysical scales of apparent heaviness in the size-weight illusion.Perception and Psychophysics, 1970,8, 225–230.Google Scholar
  25. Takane, Y., Young F. W., & deLeuw, J. Nonmetric individual differences multidimensional scaling: An alternating least squares method with optional scaling features.Psychometrika, 1967,42, 7–67.Google Scholar
  26. Tucker, L. R. Relations between multidimensional scaling and three mode factor analysis.Psychometrika, 1972,37, 3–27.Google Scholar
  27. Tucker L. R. & Messick, S. J. An individual differences model for multidimensional scaling.Psychometrika, 1963,28, 333–367.Google Scholar

Copyright information

© The Psychometric Society 1982

Authors and Affiliations

  • Terrence R. Dunn
    • 1
  • Richard A. Harshman
    • 2
  1. 1.University of MelbourneAustralia
  2. 2.University of Western OntarioCanada

Personalised recommendations