Predicting academic performance in higher education: Role of cognitive, learning and motivation

KYNDT, E. ; MUSSO, M. F. ; CASCALLAR, E. C. ; DOCHY, F.

Exeter

Congreso; 14th EARLI Conference; 2011

European Association for Research on Learning and Instruction (Earli)

There is a substantial body of literature investigating academic performance. Former research has shown that a variety of student characteristics both states and traits effect academic performance. In this research study we will predict general academic performance in the first bachelor year educational sciences, based on students´ motivation, approaches to learning, working memory capacity and attention, by means of a neural network analysis. Since the goal of a neural network analysis is classification it allows us to investigate the predictive value of the different variables for different categories of students. In this study three neural network analyses are performed for three categories of academic performers: the top 20%, the bottom 20%, and the 60% middle group of students. The relative importance of the variables will be examined in order to determine whether or not every variable is important for every category of students. Participants in this study were 128 university students. Results show that working memory capacity and attention are both good predictors of academic performance, especially for the best and weakest performers of the group. Students´ motivation and approaches to learning were good predictors for the group of students whose performance was in the middle 60%.