Classical Test Theory and Item Response Theory in Measuring Validity of Peer-Grading in Massive Open Online Courses

Abstract

The article presents the results of research on validity of peer-review assignments in massive open online courses within the framework of classical test theory (CTT) and item response theory (IRT). CTT-based analysis yielded data on convergent validity of the peer-review assignment, the low level of its criterion validity, and rater disagreement. IRT-based analysis revealed rater bias and established that experts largely tend to be lenient and overrate their peers. The findings are used to discuss the advantages and disadvantages of the psychometric theories in question and the opportunities for combining the two.