ABSTRACT
Time-series models have been the focus of considerable research and development in recent years in many disciplines, including transportation. This interest stems from the insights that can be gained by observing and analyzing the behavior of a variable over time. For example, modeling and forecasting a number of macroscopic traffic variables, such as traffic flow, speed, and occupancy, have been an indispensable part of most congestion management systems. Furthermore, forecasting passenger volumes at airport terminals is an integral input to the engineering planning and design processes. Each transportation variable that is observed over time frequently results in a time-series modeling problem where an attempt is made to predict the value of the variable based on a series of past values at regular time intervals.
