Uniqueness Proof for a Family of Models Sharing Features of Tucker's Three-Mode Factor Analysis and PARAFAC/Candecomp
- 1 March 1996
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 61 (1) , 133-154
- https://doi.org/10.1007/bf02296963
Abstract
Some existing three-way factor analysis and MDS models incorporate Cattell's “Principle of Parallel Proportional Profiles”. These models can—with appropriate data—empirically determine a unique best fitting axis orientation without the need for a separate factor rotation stage, but they have not been general enough to deal with what Tucker has called “interactions” among dimensions. This article presents a proof of unique axis orientation for a considerably more general parallel profiles model which incorporates interacting dimensions. The model, Xk=AADk HBDk B', does not assume symmetry in the data or in the interactions among factors. A second proof is presented for the symmetrically weighted case (i.e., where ADk=BDk). The generality of these models allows one to impose successive restrictions to obtain several useful special cases, including PARAFAC2 and three-way DEDICOM.Keywords
This publication has 19 references indexed in Scilit:
- PARAFAC: Parallel factor analysisComputational Statistics & Data Analysis, 1994
- The multidimensional analysis of asymmetries in alphabetic confusion matrices: Evidence for global-to-local and local-to-global processingPerception & Psychophysics, 1986
- A Model for the Analysis of Asymmetric Data in Marketing ResearchMarketing Science, 1982
- A Multidimensional Scaling Model for the Size-Weight IllusionPsychometrika, 1982
- Principal Component Analysis of Three-Mode Data by Means of Alternating Least Squares AlgorithmsPsychometrika, 1980
- A New Computational Method to Fit the Weighted Euclidean Distance ModelPsychometrika, 1978
- The Scientific Use of Factor Analysis in Behavioral and Life SciencesPublished by Springer Nature ,1978
- Analysis of individual differences in multidimensional scaling via an n-way generalization of “Eckart-Young” decompositionPsychometrika, 1970
- FACTOR ROTATION FOR PROPORTIONAL PROFILES: ANALYTICAL SOLUTION AND AN EXAMPLEBritish Journal of Statistical Psychology, 1955
- “Parallel Proportional Profiles” and other Principles for Determining the Choice of Factors by RotationPsychometrika, 1944