Title :
About the ability estimation algorithm optimization of IRT-based Computerized Adaptive Testing system
Author :
Cheng, Yan ; Xu, Weisheng ; Yu, Youling
Author_Institution :
Electron. & Inf. Eng. Coll., Tongji Univ., Shanghai
Abstract :
Aiming at the problem of Newton_Raphson algorithm calculation model for the ability estimate on the basis of the Item Response Theory (IRT) and the problem of lack of corresponding coordinating strategy when the calculating model has no root or many roots, Logistic median algorithm model and relevant coordinating strategy is put forward, compared and analyzed. Simulated experiments are conducted with the research object of three parameter logistic adaptive median algorithm model. The result shows that this Computerized Adaptive Testing (CAT) system has more superior function and lower calculation quantity, with fast convergence and the accuracy of ability estimate.
Keywords :
Newton-Raphson method; automatic test equipment; IRT-based computerized adaptive testing system; Newton-Raphson algorithm; ability estimation algorithm optimization; item response theory; logistic adaptive median algorithm model; logistic median algorithm; Adaptive control; Adaptive systems; Automatic testing; Automation; Electronic equipment testing; Intelligent control; Logistics; Maximum likelihood estimation; Programmable control; System testing; Maximum Likelihood Estimate(MLE); ability estimate; adaptive; adaptive median value algorithm; logistic model;
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
DOI :
10.1109/WCICA.2008.4593865