Sign Up

2461 SW Campus Way, Corvallis, OR 97331

View map Free Event

Speaker: Béatrice Moissinac

Traditional Item Response Theory (IRT) models the behavior of an individual's responses to a test as a function of the individual's knowledge ability, and the parameters of the test items. It is typically used in adaptive testing for quick estimation of an individual's knowledge measure. Multidimensional Item Response Theory (MIRT) extends IRT so that each item depends on multiple knowledge dimensions. MIRT models consider two opposing types of relationship between knowledge dimensions: compensatory and noncompensatory. In this work, we construct a generalization that incorporates both types of relationships: a mixed-compensation multidimensional item response theory (MCMIRT) model. We also relax the MIRT assumption that each item must include every knowledge dimension. Thus, the MCMIRT can better represent real-world curricula. We show that our approach outperforms random item selection with synthetic data.

0 people are interested in this event

User Activity

No recent activity