Precision of warm's weighted likelihood estimates for a polytomous model in computerized adaptive testing

This monte carlo study evaluated the relative accuracy of Warm's (1989) wei ghted likelihood estimate (VALE) compared to the maximum likelihood estimat e (MLE), expected a posteriori (EAP) estimate, and maximum a posteriori (MA P) estimate. The generalized partial-credit model was used under a variety of computerized adaptive testing (CAT) conditions. The results indicated th at WLE was more accurate than MLE with a fixed-length CAT, consistent with previous findings. WLE and MLE had smaller bias and larger standard errors than EAP and MAP. EAP was more accurate than MAP in a variety of CAT condit ions. Although root mean squared errors were different among the four estim ation methods, no statistically significant mean differences were found. EA P and MAP had advantages over WLE and MLE in terms of test efficiency. Thes e results suggest that the test termination rule has more impact on the acc uracy of theta estimation methods than does the item bank size.