Assessment of factor signs through logistic regression (analysis of survey results of the negative events impact on personal feelings and academic performance of Ukrainian students in 2022-2023)

Abstract

This article aims to demonstrate the possibility of using MS Excel platform to process survey results by constructing a logistic regression Multifactor Model and minimizing factor signs quantity that are associated with output change through stepwise method. Important parameters that characterize the quality and adequacy of the model are also marked: The Akaike information criterion (AIC); The Bayesian Information Criterion (BIC) and AUC stands for "Area under the ROC Curve." From the results obtained on three models, we can conclude that the morale of students during the russian invasion has a significant impact on their further intentions to continue their studies and professional work in Ukraine.