Due to the resource and time constraints for re-executing large test suites in regression testing, developers are interested in detecting faults in the system as early as possible. Test case prioritization seeks to order test cases in such a way that early fault detection is maximized. In this paper, we present a model-based heuristic method to prioritize test cases for regression testing, which takes into account two types of information collected during execution of the modified model on the test suite. The experiment shows that our algorithm has better effectiveness of early fault detection.