Vehicle re-identification methods can be used to anonymously match vehicles crossing two different locations based on vehicle attribute data. This research builds upon a previous study and investigates different methods for solving the re-identification problem and explores some of the factors that impact the accuracy of the results. To support this work, archived data from weigh-in-motion (WIM) stations in Oregon are used for developing, calibrating, and testing vehicle re-identification algorithms. In addition to the Bayesian approach developed by the researchers in the previous study, a neural network model is developed for solving the re-identification problem. The results from the testing datasets showed that both methods can be effective in solving the re-identification problem while the Bayesian method yields more accurate results. A comprehensive analysis is performed to investigate the key factors impacting the accuracy of the results. The analyses are performed by employing the Bayesian algorithm to match commercial vehicles that cross upstream and downstream pairs of WIM sites that are separated by long distances ranging from 70 to 214 miles. Data from 14 different pairs of WIM sites are used to evaluate how matching accuracy is impacted by various factors such as the distance between two sites, travel time variability, truck volumes, and sensor accuracy or consistency of measurements. After running the vehicle re-identification algorithm for each one of these 14 pairs of sites, the matching error rates are reported. The results from the testing datasets showed a large variation in terms of accuracy. It is found that sensor accuracy and volumes have the greatest impacts on matching accuracy whereas the distance alone does not have a significant impact. Overall, for estimating travel times and origin-destination flows between two WIM sites, the methods developed in this project can be used to effectively match commercial vehicles crossing two data collection sites that are separated by long distances.