A comparison of the Graded Response and Partial Credit models with a scale of Usefulness of Mathematics

The Graded Response Model (GRM) and the Partial Credit Model (PCM) of Item Response Theory (IRT) were applied in the item analysis of a scale that evaluates psychology students's beliefs about the usefulness of mathematics. The scale comprises 8 items in polytomous response format (6-point Likert-type). The sample was made up by 1875 students of the Psychology school of the University of Buenos Aires. All analyses based on IRT were performed by operating the MULTILOG software. The parameters estimation was carried out trough Marginal Maximum Likelihood procedures. Previously, the unidimensionality assumption required by the models was confirmed. The GRM showed better fit indexes than PCM and higher Test Information Function. The findings provide validity evidences based on the internal structure of scale.