This research aims to explore performance measures quantified based on different transportation data sources. It examined the major performance measures that can help describe both traffic operations and safety conditions. The available data sources that can be used to derive the performance measures were investigated. Particularly, performance measures related to travel time reliability, incident duration, and secondary crashes have been emphasized. Data-driven methodologies for performance quantification have been proposed for each category. Specifically, improved travel time estimation approaches based on probe vehicle data have been developed for traffic delays and travel time reliability analysis. Second, structure learning algorithms based on Bayesian Networks approach were proposed to mine incident records and predict incident durations that can be used for traffic incident management. Finally, both infrastructure sensor and virtual-sensor-based approaches have been developed to explore traffic sensor data as well as on-line traffic information for identifying secondary crashes. The results shown through the use of actual case studies illustrated that how key performance measures can be used to assess the performance of their systems. This research suggests that by mining existing traffic data sources, more performance measures can be more efficiently and accurately quantified without major expenditures in the deployment of new data collection technologies.