Multidimensional Student Skills with Collaborative Filtering Documents
Daniel T. Seaton, and
David E. Pritchard
Despite the fact that a physics course typically culminates in one final grade for the student, many instructors and researchers believe that there are multiple skills that students acquire to achieve mastery. Assessment validation and data analysis in general may thus benefit from extension to multidimensional ability. This paper introduces an approach for model determination and dimensionality analysis using collaborative filtering (CF), which is related to factor analysis and item response theory (IRT). Model selection is guided by machine learning perspectives, seeking to maximize the accuracy in predicting which students will answer which items correctly. We apply the CF to response data for the Mechanics Baseline Test and combine the results with prior analysis using unidimensional IRT.
- Download PERC2012_Bergner.pdf - 165kb Adobe PDF Document
Published January 24, 2013
Last Modified March 16, 2013