Assessing fit and dimensionality in least squares metric multidimensional scaling using Akaike's information criterion

Cody S. Ding, Mark L. Davison

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Akaike's information criterion is suggested as a tool for evaluating fit and dimensionality in metric multidimensional scaling that uses least squares methods of estimation. This criterion combines the least squares loss function with the number of estimated parameters. Numerical examples are presented. The results from analyses of both simulation data and real data demonstrate the utility of the Akaike's information criterion in identifying the best approximating models in multidimensional scaling analyses.

Original languageEnglish (US)
Pages (from-to)199-214
Number of pages16
JournalEducational and Psychological Measurement
Volume70
Issue number2
DOIs
StatePublished - Apr 2010

Bibliographical note

Copyright:
Copyright 2015 Elsevier B.V., All rights reserved.

Keywords

  • AIC
  • Assessing dimensionality
  • MDS

Fingerprint Dive into the research topics of 'Assessing fit and dimensionality in least squares metric multidimensional scaling using Akaike's information criterion'. Together they form a unique fingerprint.

Cite this