Predicting Underachievement in Business Statistics

Abstract

The influence of students' race and gender on their academic achievement has been the subject of numerous studies along with the development of a number of models to predict students' performance in a particular area of study (e.g., mathematics). These models, even though generally useful, tend to lose their validity when applied to a specific course. In the current investigation, a model has been developed to predict students' success and failure in a particular course (i.e., the first business statistics course). Through the use of discriminant analysis, this model was able to predict students' success and failure with approximately 72% accuracy. The model can be used to identify potential underachievers from the beginning of semesters. With such information, students who have been categorized as possible under-achievers can be monitored closely and provided with additional help in the form of tutorials and special classes, or workshops to improve their performance.