A Comparison of Exposure Control Procedures in Computerized Adaptive Testing Using the Generalized Partial Credit Model

• In Event: Test Form Development and Item Exposure

Abstract

The current study compares the progressive-restricted standard error (PR-SE) exposure control method with the Sympson-Hetter, Randomesque, and no exposure control (maximum information) procedures using the generalized partial credit model with fixed- and variable-length CATs and two item pools. The PR-SE method administered the entire item pool for all conditions, whereas the other procedures administered less than 75% of item pool 1 and less than 63% of item pool 2. PR-SE also resulted in the smallest amount of mean item overlap averaged across replications. These results were obtained with similar measurement precision compared to the other methods, except for very low theta levels (less than -2) for item pool 2, while improving on the utilization of the item pools.

Authors

• Audrey J. Leroux, Georgia State University

• Barbara G. Dodd, The University of Texas - Austin