Prediction of academic success in Electronic Engineering Technology at Texas A & M University

Abstract

This study was motivated by the need to select the most qualified applicants for the Electronic Engineering Technology program at Texas A&M University in response to the College of Engineering enrollment management policy. The objective of this study was to develop multivariate quantitative models to predict academic achievement in Electronic Engineering Technology at Texas A&M University. Subordinate objectives of the study were to determine if: (a) University entrance data of SAT scores and high school rank-in class increased the explained variance of cumulative grade point average (CUMGPA), engineering technology courses grade point average (ETGPA) and electronic engineering technology courses grade point averages (EETGPA) over other predictor variables. (b) Grades in freshman courses of pre-calculus, calculus, physics, chemistry, English, engineering design graphics and machine production techniques increased the explained variance of CUMGPA, ETGPA and EETGPA over other predictor variables. A stepwise regression method was used in the multiple regression analysis to determine the partial regression coefficients and regression constant for each of the prediction models. An F-score was calculated using Error Model 1 to determine the statistical significance of each variable as it was entered into the model in a hierarchical manner. This analysis provided multivariate quantitative models to predict CUMGPA, ETGPA and EETGPA which accounted for 56, 42 and 32 percent of the variance associated with the respective measures of academic achievement. Based on results of the study, it is recommended that the predictor models be used in selecting students for the Electronic Engineering Technology program at Texas A&M University.