A method based on 0-1 linear programming (LP) is presented to stratify an item pool optimally for use in a-stratified adaptive testing. Because the 0-1 LP model belongs to the subclass of models with a network-flow structure, efficient solutions are possible. The method is applied to a previous item pool from the CAT version of the GRE Quantitative Test. The results indicate that the new method performs well in practical situations. It improves item exposure control, reduces the MSE in the 0 estimates, and increases test reliability.
|Name||OMD research report|
|Publisher||University of Twente, Faculty of Educational Science and Technology|
- Item poolstratification
- Computerized adaptive testing (CAT)
- A-stratified adaptive testing
- 0-1 Linear programming