Differentiation between logistic regression analysis and discriminant analysis methods to reveal the factors which contribute to classify the difficulties of scientific researches that facing faculty members. (A field study on a sample of faculty members

Abstract

This study aims to determine the optimal method differentiating between discriminant analysis and binary logistic regression for classifying the challenges faced by faculty members at the University of Ajdabiya in conducting scientific research. Faculty members were categorized into two groups: those who face difficulties and those who do not.

The study also seeks to identify the most influential factors contributing to these research challenges. A simple random sampling method was employed, with data collected through a structured questionnaire.

The findings revealed that the classification accuracy of the discriminant analysis method was 85.5%, while the logistic regression method achieved a higher classification accuracy of 92.3%. Consequently, logistic regression proved to be more effective than discriminant analysis in data classification. However, both methods yielded consistent results in assessing the impact of independent variables on research challenges. The analysis identified several statistically significant variables—marital status, years of experience, subjective difficulties, and academic challenges-that influence the difficulties encountered by faculty members at the University of Ajdabiya.