基于小样本容量的IRT参数估计方法比较研究

Comparison among Parameter Estimation Methods Based on Small Sample under Item Response Theory

目前IRT参数估计方法的研究大多数都是基于大样本容量,而基于小样本容量的IRT参数估计方法的研究较少。通过对IRT参数估计方法的比较分析给出了基于小样本容量的IRT参数估计方法。实验数据表明,恰当的估计方法(如改进初值的BP神经网络)能大大提高小样本的参数估计精度。

At present, the study of IRT parameter estimation method is mostly grounded on the large sample, while the study of IRT parameter estimation method based on the small sample is less. In this paper IRT parameter estimation methods based on the small sample are proposed and comparison among these methods is made. The results of the experiment show that the accuracy of the parameter estimation on small scale sample can be greatly improved with the proper estimation method, such as the BP neural network with improving initial value.