June 20, 2010
June 20, 2010
June 23, 2010
15.1026.1 - 15.1026.17
Regression Models of Predicting Student Academic Performance in an Engineering Dynamics Course
Prediction of student academic performance helps instructors develop a good understanding of how well or how poorly the students in their classes will perform, so instructors can take proactive measures to improve student learning. Based on a total of 2,151 data points collected from 239 undergraduate students in three semesters, a new set of multivariate linear regression models are developed in the present study to predict student academic performance in Engineering Dynamics a high-enrollment, high-impact, and core engineering course that almost every mechanical or civil engineering student is required to take. The inputs (predictor/independent variables) of the models include a student’s cumulative GPA; grades earned in four prerequisite courses: Engineering Statics, Calculus I, Calculus II, and Physics; as well as scores earned in three Dynamics mid-exams. The output (outcome/dependent variable) of the models is a student’s final exam score in the Dynamics course. Multiple criteria are employed to evaluate and validate the predictive models, including R-square, shrinkage, the average prediction accuracy, and the percentage of good predictions. A good prediction is defined as the one with the prediction error of ±10%. The results show that the developed predictive models have the average prediction accuracy of 86.8%-90.7% and generate good predictions of 44.4%-65.6%. The implications of the research findings from the present study are also discussed.
Almost every mechanical or civil engineering student is required to take the Engineering Dynamics course a high-enrollment, high-impact, and core engineering course. This course is an essential basis and fundamental building block for advanced studies in many subsequent courses, such as vibration, structural mechanics, system dynamics and control, and machine and structural designs. However, many students fail this course because it covers a broad spectrum of foundational engineering concepts and principles, for example, motion, force and acceleration, work and energy, impulse and momentum, and vibrations of a particle and of a rigid body 1-3.
Prediction of student academic performance has long been regarded as an important research topic in many academic disciplines because it benefits both teaching and learning 4, 5. Instructors can use the predicted results to identify the number of students who will perform well, averagely, or poorly in a class, so instructors can be proactive. For instance, if the predicted results show that some students in the class would be “academically at risk,” instructors may consider taking certain proactive measures to help those students achieve better in the course. Representative examples of proactive measures include adding recitation sessions, adding more office hours, using computer simulations and animations to improve student problem solving, adopting a variety of active and cooperative learning strategies, to name a few.
A variety of mathematical techniques, such as multivariate linear regression 6, neural networks 7, Bayesian networks 8, decision trees 9, and genetic algorithm 10, have been employed to develop
Huang, S., & Fang, N. (2010, June), Regression Models For Predicting Student Academic Performance In An Engineering Dynamics Course Paper presented at 2010 Annual Conference & Exposition, Louisville, Kentucky. https://peer.asee.org/15759
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2010 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015