Regression with Qualitative and Quantitative Variables: An Alternating Least Squares Method with Optimal Scaling Features | Psychometrika | Cambridge Core (original) (raw)
Abstract
A method is discussed which extends canonical regression analysis to the situation where the variables may be measured at a variety of levels (nominal, ordinal, or interval), and where they may be either continuous or discrete. There is no restriction on the mix of measurement characteristics (i.e., some variables may be discrete-ordinal, others continuous-nominal, and yet others discrete-interval). The method, which is purely descriptive, scales the observations on each variable, within the restriction imposed by the variable's measurement characteristics, so that the canonical correlation is maximal. The alternating least squares algorithm is discussed. Several examples are presented. It is concluded that the method is very robust. Inferential aspects of the method are not discussed.
References
de Leeuw, J. Canonical analysis of categorical data, 1973, The Netherlands: University of Leiden.Google Scholar
de Leeuw, J. The linear nonmetric model, 1969, Leiden, The Netherlands: University of Leiden, Data Theory.Google Scholar
de Leeuw, J. Nonmetric discriminant analysis, 1968, Leiden, The Netherlands: University of Leiden, Data Theory.Google Scholar
de Leeuw, J. Normalized cone regression, 1975, The Netherlands: University of Leiden, Data Theory.Google Scholar
Hoadley, J. Spatial analysis of Senate voting patterns. Unpublished master's thesis, University of North Carolina, 1974.Google Scholar
Srinivasan, V. Linear programming computational procedures for ordinal regression. Unpublished manuscript, Graduate School of Business, Stanford University, 1974.Google Scholar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
Cliff, N. & Young, F. W. On the relation between unidimensional judgments and multidimensional scaling. Organizational Behavior and Human Performance, 1968, 3, 207–208.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, 471–503.10.1007/BF02296971CrossRefGoogle Scholar
Fisher, R. Statistical methods for research workers, 10th ed., Edinburgh: Oliver and Boyd, 1938.Google Scholar
Hayashi, C. On the quantification of qualitative data from the mathematico: Statistical point of view. Annals of the Institute of Statistical Mathematics, 1950, 2, 35–47.CrossRefGoogle Scholar
Hotelling, H. The most predictable criterion. Journal of Educational Psychology, 1935, 26, 139–142.10.1037/h0058165CrossRefGoogle Scholar
Lingoes, J. C. The Guttman-Lingoes nonmetric program series, 1973, Ann Arbor, Michigan: Mathesis Press.Google Scholar
Shepard, R. N. & Kruskal, J. B. A nonmetric variety of linear factor analysis. Psychometrika, 1974, 39, 123–157.Google Scholar
Takane, Y., Young, F. W., & de Leeuw, J. Nonmetric individual differences multidimensional scaling: An alternating least squares method with optimal scaling features. Psychometrika, in press.Google Scholar
Wold, H. & Lyttkens, E. Nonlinear iterative partial least squares (NIPALS) estimation procedures (group report). Bulletin of the International Statistical Institute, 1969, 43, 29–51.Google Scholar
Young, F. W. A model for polynomial conjoint analysis algorithms. In Shepard, R. N., Romney, A. K., & Nerlove, S. (Eds.), Multidimensional scaling, Vol. 1, 1972, New York: Seminar Press.Google Scholar
Young, F. W. Methods for describing ordinal data with cardinal models. Journal of Mathematical Psychology, 1975, 12, 416–436.CrossRefGoogle Scholar