In this paper, daily traffic counts are explained and forecast by different modeling philosophies, namely the ARIMAX and SARIMA(X) modeling approaches. Special emphasis is put on the investigation of the seasonality in the daily traffic data and on the identification and comparison of holiday effects at different site locations. To get prior insight in the cyclic patterns present in the daily traffic counts, spectral analysis provides the required framework to highlight periodicities in the data. Data originating from single inductive loop detectors, collected in 2003, 2004 and 2005, are used for the analyses. Four traffic count locations are investigated in this study, an upstream and downstream traffic count location on a highway that is excessively used by commuters and an upstream and downstream traffic count location on a highway that is typified by leisure traffic. Thedifferent modeling techniques pointed out that weekly cycles appear to determine the variation in daily traffic counts. The comparison between seasonal effects and holiday effects at different site locations revealed thatboth the ARIMAX and SARIMAX modeling approach are valid frameworks for the identification and quantification of possible influencing effects. The technique yielded the insight that holiday effects play a noticeable role on highways that are excessively used by commuters, while holiday effects have a more ambiguous effect on highways typified for their leisure traffic. Modeling of daily traffic counts on secondary roads, and simultaneous modeling of both the underlying reasons of travel, and revealed traffic patterns, certainly are challenges for further research.
Abstract