We estimate the impact of private hospital insurance on utilization of hospital care services in Australia. We employ the two-stage residual inclusion approach to address the endogeneity of private insurance. We calculate moral hazard based on a difference-of-means estimator. Our three-stage estimation framework provides evidence of selection into private hospital insurance. We find strong evidence of moral hazard when we treat hospital insurance as exogenous. After controlling for the endogeneity of hospital insurance, we find robust evidence of substitution from public to private hospital care but no evidence of ex-post moral hazard in the number of nights spent in hospital.