Bai Shengnan
School of Mathematics and Statistics, Northeast Normal University, Changchun, China.
Front Psychol. 2020 Sep 23;11:569852. doi: 10.3389/fpsyg.2020.569852. eCollection 2020.
This research focuses on developing a learning progression of probability for middle school students, and it applies the GDINA model in cognitive diagnosis models to data analysis. GDINA model analysis firstly extracted nine cognitive attributes and constructed their attribute hierarchy and the hypothesized learning progression according to previous studies, curriculum standards, and textbooks. Then the cognitive diagnostic test was developed based on Q-matrix theory. Finally, we used the GDINA model to analyze a sample of 1624 Chinese middle school students' item response patterns to identify their attribute master patterns, verify and modify the hypothesized learning progression. The results show that, first of all, the psychometric quality of the measurement instrument is good. Secondly, the hypothesized learning progression is basically reasonable and modified according to the attribute mastery probability. The results also show that the level of probabilistic thinking of middle school students is improving steadily. However, the students in grade 8 are slightly regressive. These results demonstrate the feasibility and superiority of using cognitive diagnosis models to develop a learning progression.
本研究聚焦于为中学生开发概率学习进程，并将认知诊断模型中的GDINA模型应用于数据分析。GDINA模型分析首先根据以往研究、课程标准和教科书提取了九个认知属性，并构建了它们的属性层次结构和假设的学习进程。然后基于Q矩阵理论开发了认知诊断测试。最后，我们使用GDINA模型分析了1624名中国中学生的项目反应模式样本，以识别他们的属性掌握模式，验证并修改假设的学习进程。结果表明，首先，测量工具的心理测量质量良好。其次，假设的学习进程基本合理，并根据属性掌握概率进行了修改。结果还表明，中学生的概率思维水平在稳步提高。然而，八年级的学生略有退步。这些结果证明了使用认知诊断模型来开发学习进程的可行性和优越性。
