Analysis of the Influence of Psychological Characteristics and Their Combinations on the Students' Academic Performance

Abstract

The paper presents the results of regression analysis of specially designed dataset. The students from the second to fourth year of the Novosibirsk State Technical University have passed testing procedure, among them 123 men and 68 women at the age from 18 to 23 years. The presented dataset contains the results of eight different tests. We designed this set of psychometric tests for implementing "Learner model". The "Learner model" is an important component of personal educational environment of a university. For implementing the "Learner model", we preprocess testing data and create regression models. The method of regression analysis allows exploring the most significant predictors affecting academic performance. As a result, the most significant predictors are "conscientiousness" and "behavior inhibition system". The same predictors are significant for exploring interaction effects with categorical predictors "modality", "style of reaction on changes", "gender". We also explored combinations of psychometric characteristics for finding their influence on academic problems. For this reason, we divided students into two categories, considering their academic performance. Then, we build a logistic regression model.