Raw Data_The Association Between Coaching Behaviors and Athlete Burnout Among College Athletes: An Integrated SEM–ANN Model Based on Self-Determination Theory

This dataset was collected through an online questionnaire-based survey administered via the Sojump platform between November 2025 and January 2026. Participants were college student athletes enrolled in physical education and sport-related programs at universities in several regions of China. The study aimed to examine how autonomy-supportive and controlling coaching behaviors are associated with athlete burnout and to test the mediating roles of basic psychological needs (autonomy, competence, and relatedness) within the framework of Self-Determination Theory. A probability-based random sampling strategy was used to enhance representativeness and reduce selection bias. After data screening, 800 valid responses were retained for analysis. The dataset includes demographic variables (e.g., gender, age, and academic grade level) and multiple validated psychometric measures. The core constructs include autonomy-supportive coaching behaviors, controlling coaching behaviors, autonomy, competence, relatedness, and athlete burnout. All variables were measured using standardized Likert-type instruments with established reliability and validity in sport and psychology research. The data were analyzed using a two-stage approach integrating partial least squares structural equation modeling (PLS-SEM) and artificial neural network (ANN) analysis to support both theory testing and predictive modeling. This dataset is suitable for research in sport psychology, coaching science, and athlete mental health. It is particularly useful for examining motivational climate, psychological need satisfaction, and burnout mechanisms in competitive sport contexts, and it enables both theory-driven (linear) and prediction-oriented (nonlinear) analyses.