Abstract
A traffic incident is any non-recurring event that causes a temporary reduction in the roadway capacity due to a variety of effects, such as traffic accidents, disabled vehicles, road construction, etc. Among them, traffic accidents are one of the most important events since they might lead to casualty as well as traffic congestions. Predicted accident durations are vital to the mitigation of traffic congestions caused by traffic accidents because such information alerts drivers of the necessity to re-route or re-schedule their trips. Therefore, accident duration prediction constitutes one of the most important steps in the accident management process. This study aims to investigate influential factors on large-vehicle accidents and to analyze the impacts of the factors on accident duration distributions. The results show that the accident duration distributions are significantly different among each other and thus applying different duration distributions together will contribute to more accurate prediction of accident durations.
