Application of discriminant analysis to predict the class of degree for graduating students in a university system

Abstract

In this Paper, discriminant analysis was used to predict the class of degree obtainable in a University system. The conditions for predictive discriminant analysis were obtained, and the analysis yielded a linear discriminant function which successfully classified or predicted 87.5 percent of the graduating students’ class of degrees. The function had a hit ratio of 88.2 percent when generalized, as a valid tool to classify fresh students of unknown group membership. It was also discovered that success in classifying or predicting fresh students of unknown group into classes of degree, was essentially similar to that of the historical sample. Key words: Discrimination, prediction, linear discriminant function, confusion matrix.