Component Models for Three-Way Data: An Alternating Least Squares Algorithm with Optimal Scaling Features | Psychometrika | Cambridge Core (original) (raw)

Abstract

A review of the existing techniques for the analysis of three-way data revealed that none were appropriate to the wide variety of data usually encountered in psychological research, and few were capable of both isolating common information and systematically describing individual differences. An alternating least squares algorithm was proposed to fit both an individual difference model and a replications component model to three-way data which may be defined at the nominal, ordinal, interval, ratio, or mixed measurement level; which may be discrete or continuous; and which may be unconditional, matrix conditional, or row conditional. This algorithm was evaluated by a Monte Carlo study. Recovery of the original information was excellent when the correct measurement characteristics were assumed. Furthermore, the algorithm was robust to the presence of random error. In addition, the algorithm was used to fit the individual difference model to a real, binary, subject conditional data set. The findings from this application were consistent with previous research in the area of implicit personality theory and uncovered interesting systematic individual differences in the perception of political figures and roles.

References

Harshman, R. A. Foundations of the PARAFAC procedure: Models and conditions for an “explanatory” multimode factor analysis, 1970, Los Angeles: University of California.Google Scholar

Jennrich, R. A. A generalization of the multidimensional scaling model of Carroll and Chang, 1972, Los Angeles: University of California.Google Scholar

Young, F. W., de Leeuw, J., & Takane, Y. Quantifying qualitative data, 1978, Chapel Hill, North Carolina: The L. L. Thurstone Psychometric Laboratory.Google Scholar

Young, F. W., de Leeuw, J., & Takane, Y. Multidimensional scaling: Theory and method. Book in preparation, 1981.Google Scholar

Young, F. W. Conjoint scaling, 1973, Chapel Hill, North Carolina: The L. L. Thurstone Psychometric Laboratory.Google Scholar

Schönemann, P. H., Carter, F. S., & James, W. L. Contributions to subjective metrics scaling: I. COSPA, a fast method for fitting and testing Horan’s model and an empirical comparison with INDSCAL and ALSCAL, 1976, West Lafayette, Indiana: Krannert Graduate School of Management, Purdue University.Google Scholar

EISPACK, an Eigensystem Subroutine. Argonne National Laboratory, Stanford University and University of Texas Center for Numerical Analysis, 1974.Google Scholar

Roskam, E. E. Data theory and algorithms for nonmetric scaling, 1969, Nijmegen, The Netherlands: Catholic University.Google Scholar

Sands, R. Component models for three-way data: ALSCOMP3, an alternating least squares algorithm with optimal scaling features. Unpublished Masters Thesis, University of North Carolina at Chapel Hill, 1978.Google Scholar

de Leeuw, J. A normalized cone regression approach to alternating least squares algorithms, 1977, The Netherlands: Department of Data Theory, University of Leiden.Google Scholar

Abelson, R. P. Scales derived by considerations of variance components in multi-way tables. In Gulliksen, H., & Messick, S. J. (Eds.), Psychological scaling: Theory and applications. New York: Wiley. 1960, 169–186.Google Scholar

Campbell, D. T., & Fiske, D. W. Convergent and discriminant validation by the multi-trait multi-method matrix. Psychological Bulletin, 1959, 56, 81–105.CrossRefGoogle Scholar

Carroll, J. D. Individual differences and multidimensional scaling. In Shepard, R. N., Romney, A. K., & Nerlove, S. (Eds.), Multidimensional scaling: Theory and applications in the behavioral sciences, 1972, New York: Seminar Press.Google Scholar

Carroll, J. D., & Chang, J. J. Analysis of individual differences in multidimensional scaling via an n-way generalization of “Eckart-Young” decomposition. Psychometrika, 1970, 35, 283–319.CrossRefGoogle Scholar

Cattell, R. B. The three basic factor-analysis research designs: Their interrelations and derivatives. Psychological Bulletin, 1952, 49, 499–500.CrossRefGoogle Scholar

de Leeuw, J., Young, F. W., & Takane, Y. Additive structure in qualitative data: An alternating least squares method with optimal scaling features. Psychometrika, 1976, 41, 471–503.CrossRefGoogle Scholar

Eckart, C., & Young, G. The approximation of one matrix by another of lower rank. Psychometrika, 1936, 3, 211–218.CrossRefGoogle Scholar

Guttman, L. What lies ahead of factor analysis. Education and Psychological Measurement, 1958, 18, 497–515.CrossRefGoogle Scholar

Israelsson, A. Three-way (or second order) component analysis. Bulletin of International Statistical Institute, 1969, 43, 29–47.Google Scholar

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.CrossRefGoogle Scholar

Jöreskog, K. G. Statistical analysis of sets of congeneric tests. Psychometrika, 1971, 36, 109–133.CrossRefGoogle Scholar

Kroonenberg, P., & de Leeuw, J. Principal components analysis of three mode data by means of alternating least squares algorithms. Psychometrika, 1980, 45, 69–97.CrossRefGoogle Scholar

Kruskal, J. B., & Carroll, J. D. Geometric models and badness-of-fit functions. In Krishnaiah, P. R. (Eds.), Multivariate analysis, (Vol. 2), 1969, New York: Academic Press.Google Scholar

Lingoes, J. C., & Schonemann, P. H. Alternative measures of fit for the Schonemann-Carroll Matrix Fitting Algorithm. Psychometrika, 1974, 39, 423–427.CrossRefGoogle Scholar

Messick, S., & Kogan, N. Personality consistencies in judgment: Dimensions of role constructs. Multivariate Behavioral Research, 1966, 1, 165–175.CrossRefGoogle ScholarPubMed

Mulaik, S. A. The foundations of factor analysis, 1972, New York: McGraw Hill.Google Scholar

Osgood, C. E., Suci, G. J., & Tannenbaum, P. H. The measurement of meaning, 1957, Urbana: University of Illinois Press.Google Scholar

Pederson, D. M. The measurement of individual differences in perceived personality-trait relationships and their relation to certain determinants. Journal of Social Psychology, 1965, 65, 233–258.CrossRefGoogle Scholar

Rosenberg, S., & Olshan, K. Evaluative and descriptive aspects in personality perception. Journal of Personality and Social Psychology, 1970, 16, 619–626.CrossRefGoogle ScholarPubMed

Schönemann, P. H. An algebraic solution for a class of subjective metric models. Psychometrika, 1972, 37, 441–451.CrossRefGoogle Scholar

Shepard, R. N. Metric structures in ordinal data. Journal of Mathematical Psychology, 1966, 3, 287–315.CrossRefGoogle Scholar

Sherman, R. Individual differences in perceived trait relationships as a function of dimensional salience. Multivariate Behavioral Research, 1972, 7, 109–129.CrossRefGoogle ScholarPubMed

Sherman, R., & Ross, L. B. Liberal-conservatism and dimensional salience in the perception of political figures. Journal of Personality and Social Psychology, 1972, 23, 120–127.CrossRefGoogle Scholar

Takane, Y., Young, F. W., & de Leeuw, J. Nonmetric individual differences multidimensional scaling: An alternating least squares method with optimal scaling features. Psychometrika, 1977, 42, 7–67.CrossRefGoogle Scholar

Takane, Y., Young, F. W., & de Leeuw, J. The principal components of mixed measurement level multivariate data: An alternating least squares method with optimal scaling features. Psychometrika, 1978, 43, 279–281.Google Scholar

Tucker, L. R. Implications of factor analysis of three way matrices for measurement of change. In Harris, C. W. (Eds.), Problems in measuring change. Madison: University of Wisconsin Press. 1963, 122–137.Google Scholar

Tucker, L. R The extension of factor analysis to three dimensional matrices. In Gulliksen, H., & Frederiksen, N. (Eds.), Contributions to mathematical psychology. New York: Holt, Rinehart, and Winston. 1964, 110–119.Google Scholar

Walters, H. A., & Jackson, D. N. Group and individual regularities in trait inference: A multidimensional scaling analysis. Multivariate Behavioral Research, 1966, 1, 145–163.CrossRefGoogle ScholarPubMed

Wish, M., Deutsch, M., & Biener, L. Differences in perceived similarity of nations. In Romney, A. K., Shepard, R. N., & Nerlove, S. B. (Eds.), Multidimensional scaling: Theory and applications to the behavioral sciences (Vol. 2). New York: Seminar Press. 1972, 290–314.Google Scholar

Wish, M., Deutsch, M., & Kaplan, S. J. Perceived dimensions of interpersonal relations. Journal of Personality and Social Psychology, 1976, 33, 409–420.CrossRefGoogle Scholar

Young, F. W. Nonmetric multidimensional scaling: Recovery of metric information. Psychometrika, 1970, 35, 455–474.CrossRefGoogle Scholar

Young, F. W. A model for polynomial conjoint analysis algorithms. In Shepard, R. N., Romney, A. K., & Nerlove, S. (Eds.), Multidimensional scaling: Theory and applications in the behavioral sciences, 1972, New York: Academic Press.Google Scholar

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.CrossRefGoogle Scholar

Young, F. W., & Null, C. H. Multidimensional scaling of nominal data: The recovery of metric information with ALSCAL. Psychometrika, 1978, 43, 367–379.CrossRefGoogle Scholar