Tshwane University of Technology Uses BI to Enhance First Year Student Retention

Tshwane University of Technology is using business intelligence software to develop a model that could improve first-year student retention.

"Tertiary institutions face the problem of students not completing their first year successfully, and taking too long to graduate," says Izak Smit, former statistical analyst at Tshwane University of Technology, Department of Statistical Support.

Smit and Prof. Amanda Lourens, director of research and development at Tshwane University of Technology, recently completed a research project on student retention at the Pretoria campus of the University. Smit says that they wanted to develop a statistical model to predict first-year success.

"Using SAS business intelligence software, we are designing a model that can assist in improving first-year student retention, get students to finish more quickly and limit the number of drop-outs," Smit says.

The Department of Statistical Support provides free statistical support to post-graduate students and staff. "For our students and staff, we help with experimental design, sampling protocols and questionnaire design," Smit says. "Once data has been collected, we help with the analysis, providing feedback and interpretive assistance.

"With the retention study, we wanted to use our operational database to predict the probability of students being successful in their first year. We have 5 000 student records and we classified each as a successful or unsuccessful first-year student.

"We then used 12 variables, including gender, Grade 12 aggregate, race, age and English marks, to see if any of these actually predicted first-year success. Using stepwise regression, eight variables, which were the best predictors of success, were retained in the model. A section of the 5 000 records was then used to build and calibrate a statistical model."

The remainder of the data set – unused in the model calibration – was then used to validate the model.

"Our model predicted first-year student success accurately in 75% of the cases in the validation data set," Smit says. The university will now extend this model, using additional variables including non-academic factors. "Our follow-up study will include factors such as social conditions and study environment."

The model, currently generic, will also be taken down to faculty level.

Copyright © SAS Institute Inc. All Rights Reserved.