West Virginia University
Using Machine Learning and Traditional Statistics to Explore Retention and Knowledge Structure in STEM with an emphasis on Physics
Abstract
dc:description.abstractRetention of Science, Technology, Engineering, and Mathematics (STEM) students is a serious problem as STEM graduation rates continue to lag the growing demand for the skills taught by these degree programs. Critical to fixing this “leaky pipeline” is investment in improving retention in the first two years of college study and increasing and maintaining the interest of K-12 students in STEM. This thesis will address this in three parts. The first is through evaluation of conceptual tests used to evaluate course improvements to determine the structure student knowledge measured by them. The second part uses machine learning to construct early warning models of student failure in introductory physics courses to aid instructors in better targeting of interventions. The final part assesses the effectiveness of the Pulsar Search Collaboratory, an authentic science experience for middle and high school students, at encouraging K-12 students to pursue STEM degrees.
Degree
thesis:*- Name thesis:degree_name
- PhD
- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- Physics and Astronomy
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Zabriskie, Cabot Alexander
Subjects
dc:subject × 7Identifiers
dc:identifier.*- Identifier
- https://researchrepository.wvu.edu/etd/4118