Weighted Estimation Method In Mixed Tests

For mixed-type tests composed of both dichotomous and polytomous items,polytomous items often yield more information than dichotomous items. To reflect thedifference between the two types of items and to improve the precision of abilityestimation, an adaptive weighted maximum-a-posteriori (WMAP) estimation isproposed. To evaluate the performance of WMAP, a Monte Carlo simulationcomparison is presented with maximum likelihood estimation (MLE),maximum-a-posteriori estimation (MAP), and Jeffreys modal estimation (JME).Simulation results show that the proposed method is much less biased than any of theother estimators, with relatively smaller standard errors and root-mean-square errors.