Most item selection in computerized adaptive testing is based on Fisher information (or item information). At each stage, an item is selected to maximize the Fisher information at the currently estimated trait level (theta). However, this application of Fisher information could be much less efficient than assumed if the estimators are not close to the true theta, especially at early stages of an adaptive test when the test length (number of items) is too short to provide an accurate estimate for true theta. It is argued here that selection procedures based on global information should be used, at least at early stages of a test when theta estimates are not likely to be close to the true theta. For this purpose, an item selection procedure based on average global information is proposed. Results from pilot simulation studies comparing the usual maximum item information item selection with the proposed global information approach are reported, indicating that the new method leads to improvement in terms of bias and mean squared error reduction under many circumstances.
