Using Administrative Data to Support Early Student Success: Predictors of First-Semester Performance in a Puerto Rican Public University

Authors

DOI:

https://doi.org/10.63608/ssj.4110

Keywords:

student success, first-year experience, incoming university students, administrative data, retention, higher education, quantitative analysis

Abstract

First-semester performance is a practical indicator of students’ transition into tertiary education and a point at which institutions can intervene early. This study examined an analytic dataset of 2,048 incoming students admitted to 10 academic programs in the College of Business Administration at the University of Puerto Rico, Río Piedras Campus from 2018–2019 to 2022–2023. An exploratory course-level analysis identified courses with high percentages of critical outcomes, particularly in quantitative and general education areas. Nested and cohort-specific regression models examined academic, sociofamilial, demographic, and institutional constructs associated with first-semester grade point average (GPA). Academic background produced the largest improvement in final nested model fit, which explained 28.5% of the adjusted variance in first-semester GPA. High school GPA and verbal aptitude were the most consistent predictors across cohorts. The findings support ethically designed early alert systems that use student-level indicators alongside course-level interventions to strengthen achievement, retention, and equitable student success.

Downloads

Download data is not yet available.

Author Biographies

Jairo A. Ayala-Godoy, University of Puerto Rico Río Piedras Campus

Jairo A. Ayala-Godoy is an Associate Professor in the Institute of Statistics and Computerized Information Systems, College of Business Administration, at the University of Puerto Rico, Río Piedras Campus. He holds a Ph.D. in Probability and Statistics from the Center for Research in Mathematics (CIMAT), Mexico. His research interests include applied statistics, statistical modeling, data science, statistical and data literacy, and interdisciplinary quantitative research. His work applies statistical and computational methods to problems in education, the social sciences, environmental science, and public health, and also addresses the teaching and learning of statistics and data science.

Eugenio Guerrero Ruiz, University of Puerto Rico Río Piedras Campus

Eugenio Guerrero-Ruiz is an Assistant Professor in the Department of Mathematics, College of Natural Sciences, at the University of Puerto Rico, Río Piedras Campus. He holds a Ph.D. in Probability and Statistics from the Center for Research in Mathematics (CIMAT), Mexico. His research interests include stochastic processes, stochastic differential equations, applied statistics, and Bayesian modeling, with applications to population dynamics, mortality, and life expectancy. His work focuses on developing computational and interactive resources for the teaching and learning of mathematics and statistics.

Jennifer A. Quintero-Silva, University of Puerto Rico Río Piedras Campus

Jennifer A. Quintero-Silva is a Research Assistant at the Institute of Statistics and Computerized Systems, College of Business Administration, University of Puerto Rico, Río Piedras. She holds an MBA in Operations and Supply Chain Management from the University of Puerto Rico, Río Piedras. Her research interests include the socioeconomic and academic determinants of student success, educational data analytics, and evidence-based policy for higher education. Her work applies statistical modeling and administrative data analysis to translate large, complex datasets into actionable evidence for student-centered policy, drawing on her earlier experience conducting national survey research in Colombia.

Rafael Aparicio, University of Puerto Rico at Ponce

Rafael Aparicio is an Associate Professor of Mathematics at the University of Puerto Rico at Ponce. He holds a Ph.D. in Mathematics from the University of Puerto Rico, Río Piedras Campus. His research interests include mathematical analysis, functional analysis, differential equations, and quantitative higher-education research, with particular emphasis on STEM pathways, academic performance, and student success.

Daiver Vélez-Ramos, Polytechnic University of Puerto Rico San Juan

Daiver Vélez-Ramos is an Assistant Professor of Department of Science and Mathematics at the Polytechnic University of Puerto Rico in San Juan, where he is part of the School of Arts, Sciences, and Education. He holds a Ph.D. in Mathematics from the University of Puerto Rico, Río Piedras Campus. His research interests include Bayesian statistics, statistical inference, linear models, and applied statistical methods, as well as quantitative research in higher education, with particular emphasis on academic performance and student success.

Oscar Y. Castrillón-Velandia, University of Puerto Rico Río Piedras Campus

Oscar Y. Castrillón-Velandia is an Assistant Professor in the Institute of Statistics and Computerized Information Systems, School of Business, at the University of Puerto Rico, Río Piedras Campus. He holds an Ed.D. in Curriculum and Mathematics Education from the University of Puerto Rico, Río Piedras Campus. His research interests include applied statistics, mathematics education, learning assessment, peer tutoring, and quantitative higher-education research. His work examines academic performance, student success, and institutional support in higher education through statistical and educational research approaches.

Downloads

Published

22-09-2026

How to Cite

Ayala-Godoy, J. A., Guerrero Ruiz, E., Quintero-Silva, J. A., Aparicio, R., Vélez-Ramos, D., & Castrillón-Velandia, O. Y. (2026). Using Administrative Data to Support Early Student Success: Predictors of First-Semester Performance in a Puerto Rican Public University. Student Success. https://doi.org/10.63608/ssj.4110

Issue

Online First

Section

Articles

License

Copyright (c) 2022 Jairo A. Ayala-Godoy, Eugenio Guerrero Ruiz, Jennifer A. Quintero-Silva, Rafael Aparicio, Daiver Vélez-Ramos, Oscar Y. Castrillón-Velandia

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors retain copyright and grant the Journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution International Licence (CC BY 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.