A detailed statistical analysis of pipe break records from New Haven, Connecticut, and Cincinnati, Ohio, water distribution systems focussed on deriving predictive models for pipe failure probabilities at the individual pipe level. The statistical methodology of the proportional hazards model was applied to estimate failure probabilities in the earlier phases of pipe deterioration. Another set of models, derived for pipes with frequent multiple breaks, assumed a roughly constant break rate for the later breaks. These methodologies were useful in statistically describing the failure process and in distinguishing those pipes which were most likely to break. The models provided insights into factors contributing to breaks, such as pressure, land development, soil corrosivity, and the age of the pipe. Water utilities can use the modeling of the probabilities of pipe maintenance events over time in formulating strategies for repair, replacement, and rehabilitation.