Abstract
A new procedure is discussed which fits either the weighted or simple Euclidian model to data that may (a) be defined at either the nominal, ordinal, interval or ratio levels of measurement; (b) have missing observations; (c) be symmetric or asymmetric; (d) be conditional or unconditional; (e) be replicated or unreplicated; and (f) be continuous or discrete. Various special cases of the procedure include the most commonly used individual differences multidimensional scaling models, the familiar nonmetric multidimensional scaling model, and several other previously undiscussed variants.
The procedure optimizes the fit of the model directly to the data (not to scalar products determined from the data) by an alternating least squares procedure which is convergent, very quick, and relatively free from local minimum problems.
The procedure is evaluated via both Monte Carlo and empirical data. It is found to be robust in the face of measurement error, capable of recovering the true underlying configuration in the Monte Carlo situation, and capable of obtaining structures equivalent to those obtained by other less general procedures in the empirical situation.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Reference Notes
Bloxom, B.Individual differences in multidimensional scaling (Research Bulletin 68-45). Princeton, N. J.: Educational Testing Service, 1968.
Carroll, J. D. & Chang, J. J.IDIOSCAL (Individual Differences in Orientation Scaling). Paper presented at the Spring meeting of the Psychometric Society, Princeton, N. J., April, 1972.
Carroll, J. D. & Chang, J. J.Some methodological advances in INDSCAL. Paper presented at the Spring meeting of the Psychometric Society, Stanford, California, April, 1974.
de Leeuw, J.Canonical discriminant analysis of relational data (Research Bulletin RB004-75). Leiden, The Netherlands: Datatheorie, University of Leiden, 1975.
de Leeuw, J.An initial estimate for INDSCAL. Unpublished note, 1974.
de Leeuw, J.The positive orthant method for nonmetric multidimensional scaling (Research Note RN 001-70). Leiden, TheN etherlands: Datatheorie, University of Leiden, 1970.
de Leeuw, J. & Pruzansky,^S.A new computational method to fit the weighted Euclidean model (SUMSCAL). Unpublished notes, Bell Laboratories, 1975.
Gill, P. E. & Murray, W.Two methods for the solution of linearly constrained and unconstrained optimization problems (NPL Report NAC 25). Teddington, England: National Physics Laboratory, November, 1972.
Guttman, L.Smallest space analysis by the absolute value principle. Paper presented at the symposium on “Theory and practice of measurement” at the Nineteenth International Congress of Psychology, London, 1969.
Harshman, R. A.Foundations of the PARAFAC procedure: Models and conditions for an explanatory multi-modal factor analysis (Working Papers in Phonetics No. 16). Los Angeles: University of California, 1970.
Horst, P.The prediction of personal adjustment (Bulletin 48). New York: The Social Science Research Council, 1941.
Jacobowitz, D.The acquisition of semantic structures. Unpublished doctoral dissertation, University of North Carolina, 1975.
Jones, L. E. & Wadington, J.Sensitivity of INDSCAL to simulated individual differences in dimension usage patterns and judgmental error. Paper delivered at the Spring meeting of the Psychometric Society, Chicago, April, 1973.
Kruskal, J. B., Young, F. W., & Seery, J. B.How to use KYST, a very flexible program to do multidimensional scaling and unfolding. Unpublished manuscript, Bell Laboratories, 1973.
Obenchain, R.Squared distance scaling as an alternative to principal components analysis. Unpublished notes, Bell Laboratories, 1971.
Roskam, E. E.Data theory and algorithms for nonmetric scaling (parts 1 and 2). Unpublished manuscript, Catholic University, Nijmegen, The Netherlands, 1969.
Yates, A.Nonmetric individual-differences multidimensional scaling with balanced least squares monotone regression. Paper presented at the Spring meeting of Psychometric Society, Princeton, N. J., April, 1972.
Young, F. W.Polynomial conjoint analysis: Some second order partial derivatives (L. L. Thurstone Psychometric Laboratory Report, No. 108). Chapel Hill, North Carolina: The L. L. Thurstone Psychometric Laboratory, July, 1972.
References
Bloxom, B. An alternative method of fitting a model of individual differences in multidimenlonal scaling.Psychometrika, 1974,39, 365–367.
Bôcher, M.Introduction to higher algebra. New York: MacMillan, 1907.
Carroll, J. D. & Chang, J. J. Analysis of individual differences in multidimensional scaling via anN-way generalization of “Eckart-Young” decomposition.Psychometrika, 1970,35, 238–319.
Coombs, C. H.A theory of data. New York: Wiley, 1964.
de Leeuw, J.Canonical analysis of categorical data. Leiden, the Netherlands: University of Leiden, 1973.
de Leeuw, J., Young, F. W. & Takane, Y. Additive structure in qualitative data: An alternating least squares method with opitmal scaling features.Psychometrika, 1976,41, 471–503.
Eckart, C. & Young, G. The approximation of one matrix by another of lower rank.Psychometrika, 1936,3, 211–218.
Ekman, G. Dimensions of color vision.Journal of Psychology, 1954,38, 467–474.
Fisher, R. A.Statistical methods for research workers (10th ed.). Edinburgh: Oliver and Boyd, 1946.
Funk, S., Horowitz, A., Lipshitz, R. & Young, F. W. The perceived structure of American ethnic groups: The use of multidimensional scaling in stereotype research.Sociometry, in press.
Green, P. E. & Rao, V. R.Applied multidimensional scaling: A comparison of approaches and algorithms. New York: Holt, Rinehart and Winston, 1972.
Guttman, L. A general nonmetric technique for finding the smallest coordinate space for a configuration of points.Psychometrika, 1968,33, 469–506.
Hageman, L. A. & Prosching, T. A. Aspects of nonlinear block successive overrelaxation.SIAM Journal of Numerical Analysis, 1975,12, 316–335.
Hayashi, C. Minimum dimension analysis.Behaviormetrika, 1974,1, 1–24.
Horan, C. B. Multidimensional scaling: Combining observations when individuals have different perceptual structures.Psychometrika, 1969,34, 139–165.
Johnson, R. M. Pairwise nonmetric multidimensional scaling.Psychometrika, 1973,38, 11–18.
Johnson, S. C. Hierarchical clustering schemes.Psychometrika, 1967,32, 241–254.
Jones, L. E. & Young, F. W. The structure of a social environment: A longitudinal individual differences scaling of an intact group.Journal of Personality and Social Psychology, 1972,24, 108–121.
Jöreskog, K. A general method for analysis of covariance structures.Biometrika, 1970,57, 239–251.
Kruakal, J. B. Nonmetric multidimensional scaling.Psychometrika, 1964,29, 1–27; 115–129.
Kruskal, J. B. & Carroll, J. D. Geometric models and badness-of-fit functions. In P. R. Krishnaiah,Multivariate analysis (Vol. 2), New York: Academic Press, Inc., 1969.
Lawson, C. L. & Hanson, R. J.Solving least squares problems. Englewood Cliffs, N. J.: Prentice-Hall, 1974.
Levin, J. Three-mode factor analysis.Psychological Bulletin, 1965,64, 442–452.
Levinsohn, J. R. & Young, F. W. Two special-purpose programs that perform nonmetric multidimensional scaling.Journal of Marketing Research, 1974,11, 315–316.
Lingoes, J. C.The Guttman-Lingoes nonmetric program series. Ann Arbor, Michigan: Mathesis Press, 1973.
Lingoes, J. C. & Roskam, E. E. A mathematical and empirical analysis of two multidimensional scaling algorithms.Psychometrika Monograph Supplement, 1973,38 (4, Pt. 2).
McGee, V. C. Multidimensional scaling ofn sets of similarity measures: A nonmetric individual differences approach.Multivariate Behavioral Research, 1968,3, 233–248.
Messick, S. J. & Abelson, R. P. The additive constant problem in multidimensional scaling.Psychometrika, 1956,21, 1–15.
Miller, G. A. & Nicely, P. E. An analysis of perceptual confusions among some English consonants.Journal of the Acoustical Society of America, 1953,27, 338–352.
Peterson, G. E. & Barney, H. L. Control methods used in a study of the vowels.Journal of the Acoustical Society of America, 1952,24, 175–184.
Schönemann, P. H. An algebraic solution for a class of subjective metric models.Psychometrika, 1972,37, 441–451.
Shepard, R. N. The analysis of proximities: Multidimensional scaling with an unknown distance function.I. Psychometrika, 1962,27, 125–140. (a)
Shepard, R. N. The analysis of proximities: Multidimensional scaling with an unknown distance function. II.Psychometrika, 1962,27, 219–246. (b)
Shepard, R. N. Stimulus and response generalization: Tests of a model relating generalization of distance in psychological space.Journal of Experimental Psychology, 1958,55, 509–523.
Spence, I. A Monte Carlo evaluation of three nonmetric multidimensional scaling algorithms.Psychometrika, 1972,37, 461–486.
Stevens, S. S. Mathematics, measurement, and psychophysics. In S. S. Stevens (Ed.),Handbook of experimental psychology. New York: Wiley, 1951.
Stoer, J. On the numerical solution of constrained least-squares problems.SIAM Journal of Numerical Analysis, 1971,8, 382–411.
Torgerson, W. S. Multidimensional scaling: I. Theory and method.Psychometrika, 1952,17, 401–419.
Tucker, L. R. Relations between multidimensional scaling and three-mode factor analysis.Psychometrika, 1972,37, 3–27.
Tucker, L. R. Some mathematical notes on three-mode factor analysis.Psychometrika, 1966,31, 279–311.
Wilf, H. S. The numerical solution of polynomial equations. In A. Ralston & W. S. Wilf (Eds.),Mathematical methods of digital computers (Vol. 1). New York: Wiley, 1960.
Wold, H. & Lyttkens, E. Nonlinear iterative partial least squares (NIPALS) estimation procedures.Bulletin ISI, 1969,43, 29–47.
Yates, F. The analysis of replicated experiments when the field results are incomplete.The Empire Journal of Experimental Agriculture, 1933,1, 129–142.
Young, F. W. A model for polynomial conjoint analysis algorithms. In R. N. Shepard, A. K. Romney, & S. Nerlove (Eds.),Multidimensional scaling (Vol. 1). New York: Seminar Press, 1972.
Young, F. W. Nonmetric multidimensional scaling: Recovery of metric information.Psychometrika, 1970,35, 455–474.
Young, F. W. POLYCON: A program for multidimensionally scaling one-, two-, or three-way data in additive, difference, or multiplicative spaces.Behavioral Science, 1973,18, 152–155.
Young, F. W. Methods for describing ordinal data with cardinal models.Journal of Mathematical Psychology, 1975,12, 416–436. (a)
Young, F. W. Scaling replicated conditional rank-order data.Sociological Methodology, 1975,12, 129–170. (b)
Young, F. W., de Leeuw, J., & Takane, Y. Regression with qualitative and quantitative variables: An alternating least squares method with optimal scaling features.Psychometrika, 1976,41, 505–529.
Young, F. W. & Torgerson, W. S. TORSCA, a Fortran-IV program for nommetric multidimensional scaling.Behavioral Science, 1968,13, 343–344.
Author information
Authors and Affiliations
Additional information
This project was supported in part by Research Grant No. MH10006 and Research Grant No. MH26504, awarded by the National Institute of Mental Health, DHEW. We wish to thank Robert F. Baker, J. Douglas Carroll, Joseph Kruskal, and Amnon Rapoport for comments on an earlier draft of this paper. Portions of the research reported here were presented to the spring meeting of the Psychometric Society, 1975. ALSCAL, a program to perform the computations discussed in this paper, may be obtained from any of the authors.
Jan de Leeuw is currently at Datatheorie, Central Rekeninstituut, Wassenaarseweg 80, Leiden, The Netherlands. Yoshio Takane can be reached at the Department of Psychology, University of Tokyo, Tokyo, Japan.
Rights and permissions
About this article
Cite this article
Takane, Y., Young, F.W. & de Leeuw, J. Nonmetric individual differences multidimensional scaling: An alternating least squares method with optimal scaling features. Psychometrika 42, 7–67 (1977). https://doi.org/10.1007/BF02293745
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02293745