论文部分内容阅读
本研究应用Caojing等人的Bayesian IRT Guessing系列模型,分析初中二年级学生在汉语词汇测验中的猜测行为,使用DIC3指标评价模型的拟合程度,并将参数估计结果与双参数Logistic模型进行了比较。研究发现:(1)猜测模型的拟合度优于双参数Logistic模型;(2)初中二年级测验数据最适合临界猜测模型(IRT-TG),约有3.5%的学生存在TG型猜测行为;(3)猜测者的存在会明显影响本身的能力估计与项目难度估计,但是对非猜测者的能力及区分度参数估计影响不大。
In this study, Caojing et al.’s Bayesian IRT Guessing series model was used to analyze the guesswork of second-year junior high school students in Chinese vocabulary test. The DIC3 index was used to evaluate the fitting degree of the model. The parameter estimation results were compared with the two-parameter Logistic model . The results show that: (1) the fitting degree of the prediction model is better than that of the two-parameter Logistic model; (2) The data of the second-grade junior middle school is the most suitable for the critical guess model (IRT-TG) (3) The existence of guessing players will obviously affect their own ability estimation and project difficulty estimation, but it has little effect on the non-guessing ability and discrimination parameter estimation.