Several Variations of Simple‐Structure MIRT Equating

The current study proposed several variants of simple-structure multidimensional item response theory equating procedures. Four distinct sets data were used to demonstrate feasibility methods for two different designs: a random groups design and common-item nonequivalent design. Findings indicated some notable differences between the unidimensional approaches when exhibited evidence multidimensionality. In addition, successful in providing results both section-level composite-level scores, which has not been achieved by most existing methodologies. traditional method using set quadrature points weights turned out be computationally intensive, particularly with higher dimensions. suggested an alternative way Monte-Carlo approach such data. This also true-score procedure that does rely on multivariate observed-score distribution.