Items in Context: Assessing the Dimensionality of Raven’s Advanced Progressive Matrices

• Published in: Educational and psychological measurement Vol. 65; no. 1; pp. 109 - 123
• Main Authors: Vigneau, François, Bors, Douglas A.
• Format: Journal Article
• Language: English
• Published: Thousand Oaks, CA SAGE Publications 01.02.2005; Sage Publications; Sage; SAGE PUBLICATIONS, INC
• Subjects: Biological and medical sciences; Cognition. Intelligence; College Students; Context Effect; Data Analysis; Foreign Countries; Fundamental and applied biological sciences. Psychology; Intelligence Tests; Item Response Theory; Item Sampling; Matrices; Measurement; Multidimensional Scaling; Psychology. Psychoanalysis. Psychiatry; Psychology. Psychophysiology; Psychometrics; Test Items; item response theory; Rasch model; dimensionality; Raven’s Progressive Matrices; intelligence; Context; Human; Dimensionality; Item response theory; Psychometrics; Cognition; Progressive Matrices Test Raven; Intelligence test; Principal component analysis
• ISSN: 0013-1644; 1552-3888
• DOI: 10.1177/0013164404267286

The problem of dimensionality with respect to Raven’s Advanced Progressive Matrices (APM) specifically and, more generally, g or fluid intelligence, has been a long-standing issue. The present article reports two studies examining the dimensionality of both the original Set II of the APM (n = 506) and a short form (n = 644), using principal component analysis and Rasch analysis. Although the results from the principal component analysis were equivocal, results from the Rasch analyses more strongly suggested that both forms of the test are best described as being multidimensional. Furthermore, comparison of items common to both forms indicated a context effect, thus making adaptive testing versions of this test difficult.