An effective item selection method for educational measurement
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A more effective method is proposed that can greatly reduce the error of the test information functions of parallel tests generated by other methods and should greatly aid in the construction of parallel test forms.
Abstract
Based on the test information function of the item response theory (IRT), the high quality parallel test forms can be constructed for educational measurement. Many methods have been designed to construct a test that approximates the target test for containing the similar test information functions. We propose a more effective method that can greatly reduce the error of the test information functions of parallel tests generated by other methods. Experimental results show that this method sharply reduces error with improvement ratios exceeding 96%. In addition, the computational complexity of our method is the same as that of other methods. This method should greatly aid in the construction of parallel test forms.