Applying Online Learning Analytics: Research, Findings, and Next Steps

Concurrent Session 3

Session Materials

Brief Abstract

Building a comprehensive foundation for the application of analytics is critical for online learning to demonstrate impact. This session shares insights from the current state of research on online learning analytics and recently published articles from the special issue in the Online Learning Journal. 

Presenters

Dr. Karen Vignare is a strategic innovator who has been leveraging emerging technologies to improve access, success and flexibility within higher education for over 20 years. Dr. Karen Vignare currently serves as the Executive Director of the Personalized Learning Consortium at the Association of Public and Land Grant Universities. The PLC’s mission is to support public universities as they rapidly infuse technology that supports improved student learning, retention and graduation. She has a Ph.D. from Nova Southeastern University in Computer Technology and Education and a M.B.A from the William Simon Business School at University of Rochester.
Scott is a Data Scientist with a strong interest in utilizing analytics and statistical methodologies to enhance decision making and drive policy changes in higher education. Scott currently works for PAR Framework, a division of Hobsons, where he builds predictive models, develops visual representations of data, and tackles cross-institutional research questions for partner institutions.

Extended Abstract

While research studies on the use of analytics are beginning to populate journals and conferences, many of those articles are aimed at a more limited audience of researchers. This session presents attendees with information about applying analytics within online learning while also highlighting specific studies that are particularly useful to the field. The editors of the journal from the special issue and two authors will share important contributions from the journal that will help administrators make better decisions, provide insights for faculty teaching online courses, and introduce works for other researchers to build upon.

The panel will be moderated by the editors Drs. Karen Vignare and Patsy Moskal who will review research from the recently published journal but also discuss what the current research in the field tells us about the use of online learning analytics. The discussion will also include what is missing in the field and where both practitioners and researchers need to focus their research efforts. The Online Learning Journal special issue on learning analytics represents universities that are using analytics, researchers who are publishing, colleagues within practitioner communities, and implementers of analytics within online universities.

The two authors will share details on their recently published work. Dr. Karen Swan, representing James, Swan and Daston (2016), will discuss the review of a large dataset compiled within the Predictive Analytics Reporting (PAR) Framework that was used to compare students enrolled in only on-ground courses, students enrolled in only online courses, and students enrolled a mixture of both modalities at five primarily on-ground community colleges, five primarily on-ground four-year universities, and four primarily online institutions. This exciting work entitled, “Retention, Progression and the Taking of Online Courses,” provides further proof that online courses can provide both flexibility and access while improving student completion. The results suggest that taking online courses is not necessarily harmful to students’ chances of being retained. While the PAR Framework dataset represents a microcosm of institutions across American universities, it does include a more representative sample of institutions serving nontraditional students. It is clear from other work including IPEDS recent reports that these students are taking more accessible course modalities like online and blended courses. The research also reveals essentially no difference in retention between delivery mode for students enrolled in primarily on-ground four-year universities participating in the PAR Framework. At participating primarily online institutions, students blending their courses had slightly better odds of being retained than students taking exclusively on-ground or exclusively online courses. This report furthers other seminal research that reviews retention in online and blended learning.

The last paper discussed will share a case study from a large public online university where analytics were used to predict the success of transfer students. The research study examines student learner characteristics, course-taking behaviors from prior community colleges attended, and first-term GPA at a four-year institution to predict the likelihood of re-enrollment for 8,200 students.  The logistic regression models showed that gender, age, and first term GPA at the four-year institution were significant predictors of re-enrollment. 

The session will include time for audience questions.