Predicting Student Success in Computer Science – A Reproducibility Study

Abstract

(Research Category/Full paper) — A recent study conducted at the University of Oklahoma, a large research university attempted to use the grades on initial Computer Science courses to predict the success of Computer Science majors. We attempted to reproduce this study in a mid-sized liberal arts institution. We analyzed 15 years of data of students (majors as well as non-Computer Science majors) who had taken introductory Computer Science courses. We found that the better the grade on Computer Science I, the introductory course in the major, the better the cumulative GPA of the student upon graduation, and this applied to Computer Science majors as well as non-majors. All the students who had successfully graduated with a Computer Science degree had earned at least a C grade in the first three required courses: Computer Science I, Computer Science II and Data Structures. When we considered grades on six of the required courses in the Computer Science sequence, we found that students generally earned the same or lower grade on each subsequent course. Therefore, the performance of Computer Science majors on the first three courses in the required course sequence can reasonably be used as predictors of their success in the major. Finally, we found that Math SAT score was a good predictor of student success in Computer Science I as well as obtaining an undergraduate degree regardless of the major. Our study generalizes the results of the previous study and strengthens the results by finding that they are statistically significant. (Abstract)