Traffic incidents occur frequently on urban roadways and cause incident-induced congestion. Predicting incident duration is a key step in managing these events. Ordinary least squares (OLS) regression models can be estimated to relate the mean of incident duration data with its correlates. Because of the presence of larger incidents, duration distributions are often right-skewed; that is, the OLS model underpredicts the durations of larger incidents. Therefore, this study applies a modeling technique known as quantile regression to predict more accurately the skewed distribution of incident durations. Quantile regression estimates the relationships between correlates and a chosen percentile—for example, the 75th or 95th percentile—while the OLS regression is based on the mean of incident duration. With the use of incident data related to more than 85,000 (2013 to 2015) incidents for highways in the Hampton Roads area of Virginia, quantile regression results indicate that the magnitudes of parameters and predictions can be quite different compared with OLS regression. In addition to predicting durations of larger incidents more accurately, quantile regressions can estimate the probability of an incident lasting for a specific duration; for example, incidents involving congestion and delay have an approximately 25% chance of lasting more than 100.8 min, while incidents excluding congestion and delay are estimated to have a 25% chance of lasting more than 43.3 min. Such information is helpful in accurately predicting durations and developing potential applications for using quantile regressions for better traffic incident management.

Traditionally, evaluation of intersection safety has been largely reactive and based on historical crash frequency data. However, the emerging data from connected and autonomous vehicles can complement historical data and help in proactively identifying intersections with high levels of variability in instantaneous driving behaviors before the occurrence of crashes. On the basis of data from the Safety Pilot Model Deployment in Ann Arbor, Michigan, this study developed a unique database that integrated intersection crash and inventory data with more than 65 million real-world basic safety messages logged by 3,000 connected vehicles; this database provided a more complete picture of operations and safety performance at intersections. As a proactive safety measure and a leading indicator of safety, location-based volatility was introduced; this quantified variability in instantaneous driving decisions at intersections. Location-based volatility represented the driving performance of connected-vehicle drivers traveling through a specific intersection. As such, with the use of the coefficient of variation as a standardized measure of relative dispersion, location-based volatility was calculated for 116 intersections in Ann Arbor. Rigorous fixed- and random-parameter Poisson regression models were estimated to quantify relationships between intersection-specific volatilities and crash frequencies. Although exposure-related factors were controlled for, the results provided evidence of a statistically significant (at the 5% level) positive association between intersection-specific volatility and crash frequencies for signalized intersections. The implications of these findings for proactive intersection safety management are discussed.