Rising standards of living and the trend towards shorter working hours have led to significant changes in traffic volume during holiday periods. The challenge of holiday traffic has been reported worldwide in the literature. A comprehensive understanding of the changes in traffic volume patterns associated with holiday events are very critical to many transportation engineering aspects such as traffic control, signal timing, road safety, and traffic volume monitoring, imputation, and prediction. However, existing research focusing on holiday traffic has been very little to date, and the efforts made have generally been limited to a particular holiday period or a specific recreational area. This paper presents a non-parametric hypothesis test method to examine the changes in traffic volume patterns due to holidays. The data used in this study are traffic volumes collected from Canadian highway networks over the past 20 years. To illustrate the application and effectiveness of the proposed method, in-depth investigations are carried out with respect to the variation of both weekly and daily volumes during a total of 12 Canadian holiday periods. The test results show that, for various types of roads, this method is effective and easy to understand. Moreover, the outputs are very informative and reasonable. It is believed that this method may also be a useful tool to examine the variation characteristics of traffic during other special time periods
Samenvatting