AHM分类方法的改良

Improvement of Classification Methods of AHM

对AHM模型2种基于IRT的判别方法——方法 A和方法 B进行改良,得到方法 C和方法 D.通过蒙特卡洛模拟试验考察A、B、C、D等4种方法的诊断性能.结果表明:蒙特卡洛模拟试验的结果与理论研究结果相符,方法 C优于方法 A,方法 D优于方法 B,且从总体上看新方法的评价指标比对应原方法的评价指标有较大幅度的提高.

Two traditional methods, Method A and Method B, based on item response theory are presented by Leighton to illustrate the classification of observed response patterns in the AHM. But their diagnostic accuracy is not high. This study presents two new classification methods, Method C and Method D, based on item response theory, which varied from the two traditional methods. A Monte Carlo simulation experiment is designed tO explore the performance of different methods. The results show that the diagnostic performance of new methods is better than the traditional methods. The pattern match ratio （PMR） and marginal match ratio （MMR） of Method C is higher than Method A. The pattern match ratio （PMR） and marginal match ratio （MMR） of Method D is higher than Method B.