Automobile demand has been widely and extensively investigated because of its effects on many related fields such as travel behavior, public policy and management, and transportation impact analysis. Although its importance has been well perceived in the field of transportation, the models developed frequently emphasize short-term forecasting, and interactions and simultaneity among the endogenous variables are rarely investigated. In addition, a large number of existing models adopt simple regression methods with time-series data. However, the approach may produce inconsistent estimates due to simultaneities of many other endogenous variables. A structural equation model has been constructed to estimate aggregated automobile demand with data from Korea. The model framework includes several endogenous and exogenous variables. The findings show significant interrelationships and simultaneities among automobile demand, driver population, and road length, and all exogenous variables strongly affect the endogenous variables as well. The model can be used as a basis for forecasting future automobile demand.
Abstract