Testing Pattern Hypotheses with MDS

  • Cody S. Ding


Discuss how to conduct confirmatory MDS analysis of profile similarities in the context of configuration comparison. Model fit between hypothesized and observed profiles can be assessed with respect to local fit index rather than global fit index. Local fit can be assessed using correlation r, t-test or ANOVA, and F-test. An example is provided to demonstrate the idea.


Profile similarity Local fit Global fit 


  1. Borg, I., Groenen, P. J. F., & Mair, P. (2013). Applied multidimensional scaling. Berlin: Springer.CrossRefGoogle Scholar
  2. Carroll, J. D., & Wish, M. (1973). Models and methods for three-way multidimensional scaling. In R. C. Atkinson, D. H. Krantz, R. D. Luce, & P. Suppes (Eds.), Contemporary developments in mathematical psychology. San Francisco: W. H. Freeman.Google Scholar
  3. Cronbach, L. J., & Gleser, G. C. (1953). Assessing similarity between profiles. Psychological Bulletin, 50, 456–473.CrossRefGoogle Scholar
  4. Gower, J. C. (1975). Generalised procrustes analysis. Psychometrika, 40, 33–51.MathSciNetCrossRefGoogle Scholar
  5. MacKay, D.B., & Zinnes, J. (2014). PROSCAL professional: A program for probabilistic scaling:
  6. McCrae, R. R. (1993). Agreement fo personality profiles across observers. Multivariate Behavioral Research, 28(1), 25–40.CrossRefGoogle Scholar
  7. Park, I., & Schutz, R. W. (2005). An introduction to latent growth models: Analysis of repeated measures physical performance data. Research Quarterly for Exercise and Sport, 76(2), 176–192.CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Cody S. Ding
    • 1
    • 2
  1. 1.Department of Education Science and Professional ProgramUniversity of Missouri-St. LouisSt. LouisUSA
  2. 2.Center for NeurodynamicsUniversity of Missouri-St. LouisSt. LouisUSA

Personalised recommendations