English

Quantifying the relationship between student enrollment patterns and student performance

Physics Education 2020-11-10 v4 Machine Learning Applications Machine Learning

Abstract

Simplified categorizations have often led to college students being labeled as full-time or part-time students. However, at many universities student enrollment patterns can be much more complicated, as it is not uncommon for students to alternate between full-time and part-time enrollment each semester based on finances, scheduling, or family needs. While prior research has established full-time students maintain better outcomes then their part-time counterparts, limited study has examined the impact of enrollment patterns or strategies on academic outcomes. In this paper, we applying a Hidden Markov Model to identify and cluster students' enrollment strategies into three different categorizes: full-time, part-time, and mixed-enrollment strategies. Based the enrollment strategies we investigate and compare the academic performance outcomes of each group, taking into account differences between first-time-in-college students and transfer students. Analysis of data collected from the University of Central Florida from 2008 to 2017 indicates that first-time-in-college students that apply a mixed enrollment strategy are closer in performance to full-time students, as compared to part-time students. More importantly, during their part-time semesters, mixed-enrollment students significantly outperform part-time students. Similarly, analysis of transfer students shows that a mixed-enrollment strategy is correlated a similar graduation rates as the full-time enrollment strategy, and more than double the graduation rate associated with part-time enrollment. Such a finding suggests that increased engagement through the occasional full-time enrollment leads to better overall outcomes.

Cite

@article{arxiv.2003.10874,
  title  = {Quantifying the relationship between student enrollment patterns and student performance},
  author = {Shahab Boumi and Adan Vela and Jacquelyn Chini},
  journal= {arXiv preprint arXiv:2003.10874},
  year   = {2020}
}
R2 v1 2026-06-23T14:25:29.688Z