When tests are made up of testlets, a testlet-based item response theory (IRT) model may be used to account for local dependence among items from a common testlet. This study presents a new test characteristic curve method to link calibrations based on the Bradlow, Wainer, and Wang (1999) testlet model. Procedures for calculating the test characteristic curve linking coefficients are developed. The effectiveness of the method is investigated using simulated data. Results suggest that the linking coefficients are accurately recovered and superior to those obtained when using a traditional IRT model to link calibrations when testlet-based local dependence is present. A real data example illustrates the proposed linking method.
No takes yet. Share an insight, caveat, or question.
Bolt et al. (2005) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: