In this paper we present a measurement-based approach that produces both a WCET (Worst Case Execution Time) estimate, and a prediction of the probability that a future execution time will exceed our estimate. Our statistical-based approach uses extreme value theory to build a model of the tail behavior of the measured execution time value. We validate our approach using an industrial data set comprised of over 150 sampled components and nearly 200 million sample execution times. Each trace is divided into two segments, with one used to make the WCET estimate, and the second used check our prediction of the fraction of future execution time samples that exceed our WCET estimate. We show that compared to WCET estimates derived from the worst-case observed time, our WCET estimates significantly improve the ability to predict the probability that our WCET estimate is exceeded.