Modeling student pathways in a physics bachelor's degree program
Modeling student pathways in a physics bachelor's degree program
复制标题
DOI：
10.1103/physrevphyseducres.15.010128
复制
发表时间：
2019-05-15
影响因子：
3.1
通讯作者：
Caballero, Marcos D.
中科院分区：
文献类型：
--
作者：
Aiken, John M.;Henderson, Rachel;Caballero, Marcos D.
物理教育研究（PER）使用定量建模技术来探索物理教育的学习，情感和其他方面。然而，这些研究很少检查模型的预测输出，而是专注于在各种数据集中观察到的推论或因果关系。本研究介绍了一个现代的预测建模方法，以PER社区使用成绩单数据的学生宣布在密歇根州立大学物理专业。使用机器学习模型，该分析表明，从物理学位课程切换到工程学位课程的学生不参加热力学和现代物理学的第三学期课程，并且可以在注册为物理专业时参加工程课程。以年级以及学生宣称的性别和种族来衡量的入门物理和微积分课程的表现，相对于模型中包含的其他特征，所起的作用要小得多。这些结果被用来比较传统的统计分析，一个更现代的建模方法。
Physics education research (PER) has used quantitative modeling techniques to explore learning, affect, and other aspects of physics education. However, these studies have rarely examined the predictive output of the models, instead focusing on the inferences or causal relationships observed in various data sets. This research introduces a modern predictive modeling approach to the PER community using transcript data for students declaring physics majors at Michigan State University. Using a machine learning model, this analysis demonstrates that students who switch from a physics degree program to an engineering degree program do not take the third semester course in thermodynamics and modern physics, and may take engineering courses while registered as a physics major. Performance in introductory physics and calculus courses, measured by grade as well as a students' declared gender and ethnicity play a much smaller role relative to the other features included in the model. These results are used to compare traditional statistical analysis to a more modern modeling approach.