Session Y08: Big Data in Physics Education Research

Live

Retention of STEM students is a critical national problem. Introductory physics classes play a key role in the retention of these students. Machine learning algorithms including decision trees and random forests are applied to understand the variables important in predicting retention through the first year of college. This analysis identifies being a successful student in high school and arriving on campus “calculus-ready” as critical predictors of success. The student’s progression through the network of introductory science and mathematics courses is then explored. Machine learning algorithms are applied to understand a student’s risk factors as they matriculate from Calculus 1 and Chemistry 1 through Physics 1 and Physics 2. This will show students who matriculate through the network along different paths have different risk factors and chances of success.   

Live

Historically, Physics Education Research (PER) have collected and analyzed quantitative data sources using traditional statistical and modeling techniques. As educational research advances, quantitative data sets have become more robust and complex. Here, we will discuss the quantitative research being done in the Learning Machines Lab--a collaboration between Michigan State University (MSU) and the University of Oslo (UiO)--where graduate students, post-docs, and undergraduate researchers, are conducting cutting-edge research on large data sets. These projects include using innovative big data research methods including machine learning techniques to explore solutions to complex educational research questions. In this talk, the various projects will be highlighted including the variety of data sources, the innovative research methods, and the central outcomes of these studies.   

Live

How can we create inclusive undergraduate STEM learning environments, which allow diverse populations of students to thrive? Previous research has shown that the first two years of undergraduate education is critical in pursuing STEM fields and retention in general. In particular, performance in introductory STEM courses is a key indicator of pursuing STEM fields. In this talk, I will present two research studies exploring the demographic performance gaps in introductory STEM courses using large data sets across four different universities and various STEM introductory courses. Such large data sets enabled us to conduct more thorough analysis for examining possible mechanisms behind the demographic performance gaps. The analysis shows that this underperformance is dominated by the incoming preparation of the students, as opposed to other possible factors such as social psychological factors. I will conclude with some suggestions as to how these findings might be used to guide educators to design more effective interventions to support the success of students from underrepresented demographic groups in their introductory STEM courses at Stanford and elsewhere.