A mathematical programming approach is presented for computer adaptive testing (CAT) with many constraints on the item and test attributes. Because mathematical programming problems have to be solved while the examinee waits for the next item, a fast implementation of the Branch-and-Bound algorithm is needed for this approach. Eight modifications of the algorithm especially designed for application in CAT are described. In order to investigate the effects of the modifications, two empirical examples using simulation were studied. The modified Branch-and-Bound algorithm selected the items in the adaptive tests in a realistic amount of time, while the resulting tests met the constraints.
|Name||OMD research report 00-05|
|Publisher||University of Twente, Faculty of Educational Science and Technology|