This study focuses on developing methodologies to predict the service life of a pavement marking material based on its retrorefl ectivity. Data from the 2002 National Transportation Product Evaluation Program (NTPEP) pavement marking material test deck in Mississippi are used for model development and model validation. The smoothing spline method and time series modeling are applied to estimate the service lives of different types of materials based on the assumption of a required minimum retrorefl ectivity value. The same models can also predict the retrorefl ectivity values at future times for a pavement marking product based on its retrorefl ectivity values in the past. The validation of the models shows satisfactory accuracy. As demonstrated in a case study, the predicted service lives of the marking materials can be used in life-cycle cost comparisons for selecting pavement marking material.