Measuring Long-Run Price Elasticities in Urban Travel Demand

This paper develops a structural model of urban travel to estimate long-run price elasticities. A dynamic discrete choice demand model with switching costs is estimated, using a panel dataset with public market-level data on automobile and public transit use for Chicago. The estimated model shows that long-run own- (automobile) and cross- (transit) price elasticities are more elastic than short-run elasticities, and that elasticity estimates from static and myopic models are downward biased. The estimated model is used to evaluate the response to a gasoline tax. Static and myopic models mismeasure long-run substitution patterns, and could lead to incorrect policy decisions.