Data-crunching is helping colleges get more students to a degree, reports Joseph B. Treaster in the New York Times.
At Georgia State’s nursing school, the faculty used to believe that doing well in an introductory nursing class predicted who’d graduate. “Predictive analytics” showed that students could recover from a C in nursing — but not in math.
. . . fewer than 10 percent of nursing students with a C in math graduated, compared with about 80 percent of students with at least a B+. Algebra and statistics, it seems, were providing an essential foundation for later classes in biology, microbiology, physiology and pharmacology.
The University of Arizona discovered that earning an A or B in the first-year writing course is a critical step to a degree. UA is devoting more resources to the course and to helping weaker students improve.
Credit: Mirko Illic
A variety of factors go into predictive analytics, writes Treaster. In addition to test scores and grades, personal information and coursework, programs analyze “how frequently (students) are seeing advisers and tutors and how actively they are engaging in the campus networks where professors post homework assignments, lecture notes, comments and grades.”
Companies promise colleges they can identify when a student goes off the success track, as defined by previous students. That can alert an advisor to check in with the student.
Georgia State, which uses analytics, doubled its advising staff. The six-year graduation rate rose 6 points, to 54 percent.