Item and error analysis on Raven's Coloured Progressive Matrices in Williams Syndrome

Abstract

Raven's Coloured Progressive Matrices (RCPM) is a standardised test that is commonly used to obtain a non-verbal reasoning score for children. As the RCPM involves the matching of a target to a pattern it is also considered to be a visuo-spatial perception task. RCPM is therefore frequently used in studies in Williams Syndrome (WS), in order to match WS participants to a control group or as a single measure to predict performance on a test-condition in developmental trajectory analyses. However, little is known about the performance of participants with WS on the RCPM. The current study compared the type of errors and the difficulty of each item for 53 participants with WS to 53 typically developing children who were individually matched on the total raw score for RCPM. Results showed that the participants with WS made the same proportion of error types and that the proportion of error types changed similarly to those of typically developing controls over development. Furthermore, the differential item difficulty between the two groups was highly similar. It is therefore argued that, although participants with WS are delayed on RCPM, their performance is not atypical which suggests that RCPM performance is supported by typical mechanisms. The RCPM is therefore a useful tool to match WS to control groups or to construct developmental trajectories.