The effect of model misspecification on classification decisions made using a computerized test

Many computerized testing algorithms require the fitting of some item respo nse theory (IRT) model to examinees' responses to facilitate item selection , the determination of test stopping rules, and classification decisions. S ome IRT models are thought to be particularly useful for small volume certi fication programs that wish to make the transition to computerized adaptive testing (CAT). The one-parameter logistic model (I-PLM) is usually assumed to require a smaller sample size than the three-parameter logistic model ( 3-PLM) for item parameter calibrations. This study examined the effects of model misspecification on the precision of the decisions made using the seq uential probability ratio test (SPRT). For this comparison, the I-PLM was u sed to estimate item parameters, even though the items characteristics were represented by a S-PLM. Results demonstrated that the I-PLM produced consi derably more decision errors under simulation conditions similar to a real testing environment, compared to the true model and to a fixed-form standar d reference set of items.