Learning Analytics and Online Student Success: Using LMS Behavioral Data to Predict Academic Performance

Author

• Luis Alberto Azpeitia, The University of Texas Rio Grande Valley

Date of Award

7-1-2026

Document Type

Dissertation

Degree Name

Doctor of Education (EdD)

Department

Curriculum & Instruction

First Advisor

Maria Elena Corbeil

Second Advisor

Beatrice R. Buentello

Third Advisor

Joseph Rene Corbeil

Abstract

This quantitative nonexperimental correlational study examined whether learning management system (LMS) behavioral trace data could predict academic performance in fully online asynchronous courses. Set at a Hispanic Serving Institution, the study used 155 student records drawn from multiple sections of a single education course, allowing engagement to be examined within a consistent instructional context. The work was grounded in self-regulated learning and student engagement theory, which treat observable LMS activity as a proxy for the effort behind academic success. Two questions guided the study: whether LMS engagement predicted final course grades, and whether engagement differed across student performance levels. A broad set of behavioral trace variables, including submissions, time on task, and resource access, was prepared and analyzed through multiple regression and multivariate analysis of variance. By concentrating on one course taught across several sections, the study addressed a persistent challenge in learning analytics: the limited portability of predictive models across contexts. The findings were framed as associative rather than causal.

Comments

Copyright 2026 Luis Alberto Azpeitia. All Rights Reserved. https://proquest.com/docview/3408953529

Recommended Citation

Azpeitia, L. A. (2026). Learning Analytics and Online Student Success: Using LMS Behavioral Data to Predict Academic Performance [Doctoral dissertation, The University of Texas Rio Grande Valley]. ScholarWorks @ UTRGV. https://scholarworks.utrgv.edu/etd/2018