Objectives. This primary objective of the study was to examine the direct and moderating effects of hardiness on the prediction of sport injury, and the direct and indirect effects of hardiness on athletes’ responses to injury.Design. This study employed a longitudinal methodological design. Specifically, the injury status of 694 asymptomatic participants was monitored for 2 years. From the original sample, 104 athletes subsequently became injured and then completed a number of questionnaires throughout their recovery.Methods. Logistic regression, Pearson product‐moment correlation and Preacher and Hayes's (2008) bootstrapping procedure were used to analyse the data.Results. Findings revealed a direct and moderating effect of hardiness on the prediction of injury. Hardiness was also found to positively correlate with desirable, and negatively correlate with undesirable post‐injury psychological responses and coping strategies throughout recovery. Finally, problem‐focused coping was found to mediate certain effects of hardiness on injured athletes’ psychological responses.Conclusions. These findings have important implications for practitioners who have a vested interest in the health and well‐being of those who participate in sport and exercise in terms of minimizing rates of injury occurrence and/or facilitating recovery from injury.