Work In Progress: Engineering Students´ Change in Profile over the Freshman Year across Male and Female Samples: An Neural Network Approach

The differential change of incoming male and female engineering students´ self-beliefs over the freshman year hold critical import for continuous improvement in first-year engineering education. Whether male and female students hold similar noncognitive self-beliefs upon entering college, and if they change similarly over the freshman year, are examined. Thus, the objective of this work-in-progress has been to develop an artificial neural network (NN), which uses the noncognitive attributes identified in our previous research (9 factors defined by 166 items) as independent parameters to predict student success, which is operationalized in terms of grade-point-average (GPA) and persistence (within engineering school) at the end of first year. The noncognitive measures include: academic self-efficacy, academic motivation, leadership, metacognition, major indecision, type of learner (e.g., deep vs. surface), teamwork, and expectancy-value. An analysis of the NN´s ability to predict students´ success based upon their initial responses and their differential change is presented as well as an analysis based upon gender