Virtual On line
June 22, 2020
June 22, 2020
June 26, 2021
Educational Research and Methods
This research paper discusses a new, data-driven metric for measuring retention. First and second year retention and retention rates are now well established as metrics in the engineering education research landscape, with many research studies exploring the impact of individual performance, noncognitive, and preparation characteristics on retention in engineering. Researchers at the University of Louisville, a large Research Institution in the Midwest, have compiled survey results and enrollment data for students in the engineering college since 2010, with the intention of conducting retrospective studies of engineering retention using this data. Using “degree earned in six years or less” to label students as retained makes over half the dataset unusable. First and second year retention are options, but these can have both false positives and false negatives. Using a data science pipeline, we analyzed the number of consecutive non-enrolled terms, referred to as enrollment gaps, and found that the best short-term criteria is “three consecutive semesters not enrolled in engineering.” With this criterion, we can reliably label a given student as not-retained. The proposed retention threshold approach has the following advantages: It does not rely on the requirement of earning a degree in engineering and could be applied across a variety of fields of study, it is not based on enrollment at a fixed point in time, and it can be used as the data set continues to grow. Most importantly, while other common heuristics use grades, success in certain consecutive courses, or even demographics; our method only uses enrollment (and hence enrollment gap) data. This is a significant advantage given that the enrollment data is always available; whereas other commonly used feature heuristics for retention determination are not always available or may only apply to subsets of students.
Boujelbene, M., & Damak, K., & Acun Sener, A. C., & Hieb, J. L., & Bego, C. R., & Ralston, P. A., & Nasraoui , O. (2020, June), A Data-science Approach to Flagging Non-retention in Engineering Enrollment Data Paper presented at 2020 ASEE Virtual Annual Conference Content Access, Virtual On line . 10.18260/1-2--33996
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2020 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015