Although most computerized adaptive tests (CATs) use dichotomous item response theory (IRT) , research on the use of polytomous IRT in CAT has shown promising results. This implemented a CAT based on the nominal model (NR CAT). Item pool requirements the NR CAT were examined. The performance of NR CAT and a CAT based on the three-parameter (3PL) model was compared. For two-, three-, four-category items, items with maximum of at least .16 produced reasonably trait estimation for tests with a minimum length of approximately 15 to 20 items. The CAT was able to produce trait estimates to those of the 3PL CAT. Implications these results are discussed. Index terms: testing; computerized adaptive testing; EAP ; nominal response model; polytomous .
No takes yet. Share an insight, caveat, or question.
R. J. De Ayala (1992) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: