Dataset on Digital Literacy, Creative Thinking Disposition, And Generative Artificial Intelligence Literacy as Predictors of Academic Performance of Pre-service Visual Art TeacherS in Ghana

Abstract

This dataset provides empirical evidence on how digital literacy, generative AI (GenAI) literacy, and creative thinking disposition interact to predict academic performance among 258 pre-service Visual Arts teachers in Ghana. Grounded in Connectivism and Self-Determination Theory, it captures the growing demand for integrated technological and cognitive competencies in resource-constrained higher education contexts. Using a hybrid analytical approach combining Partial Least Squares Structural Equation Modelling (PLS-SEM), Importance-Performance Map Analysis (IPMA), and Necessary Condition Analysis (NCA), the dataset supports both explanatory and diagnostic modelling of complex relationships. Findings indicate that creative thinking disposition is the strongest predictor of academic performance, followed by digital literacy, while GenAI literacy exerts a significant indirect effect through creativity. The model explains 66% of the variance in academic performance, with all three competencies identified as necessary conditions with threshold effects. Structured on validated 7-point Likert-scale measures and ready for use across statistical platforms, the dataset enables replication, mediation and moderation analysis, and advanced techniques such as fsQCA and predictive modelling. It is particularly valuable for research on AI literacy, digital competence, and creativity in low-resource settings. By foregrounding an African perspective, this dataset challenges technology-centric narratives and demonstrates that the real driver of academic performance is not access to tools alone, but the creative capacity to transform them into meaningful learning outcomes.