When should a government provide a service in-house, and when should it contract out provision? We develop a model in which the provider can invest in improving the quality of service or reducing cost. If contracts are incomplete, the private provider has a stronger incentive to engage in both quality improvement and cost reduction than a government employee has. However, the private contractor's incentive to engage in cost reduction is typically too strong because he ignores the adverse effect on noncontractible quality. The model is applied to understanding the costs and benefits of prison privatization.