A PYTHON-BASED ANALYSIS OF ACADEMIC PERFORMANCE AND AGE ON ADMISSION OF STUDENTS IN SOME SELECTED UNIVERSITIES IN SOUTH-WESTERN PART OF NIGERIA

Abstract

Understanding the influence of admission age on students’ academic performance remains a persistent concern in higher education, particularly in developing contexts where entry standards are inconsistently enforced. This study investigates the relationship between students’ age at admission and their academic outcomes using a Python-based data analytics approach. A dataset comprising 1,401 undergraduate records from Fountain University, Osogbo, and the Federal University of Agriculture, Abeokuta located in the South-West region of Nigeria, spanning 2014–2024, was analyzed. Python libraries such as pandas, matplotlib, and scipy.stats were employed for data cleaning, visualization, and statistical testing. Descriptive analysis revealed that most students were admitted between ages 16 and 20, with a near-equal gender distribution. Inferential results indicated no statistically significant difference in academic performance across age groups (ANOVA, p = 0.1077), suggesting that admission age exerts minimal effect on cumulative grade point average (CGPA). However, gender-based comparison showed a significant difference (t-test, p < 0.001), with female students outperforming their male counterparts. These findings imply that cognitive maturity associated with age is less decisive for academic success than factors such as motivation and discipline, which may explain the observed gender disparity. The study underscores the potential of Python-driven analytics for evidence-based educational evaluation and advocates for gender-responsive academic support policies rather than rigid age-based admission criteria.