Structure of Public Transit Costs in the Presence of Multiple Serial Correlation

Most studies indicate that public transit systems operate under increasing returns to capital stock utilization and are significantly overcapitalized. Existing flexible form time series analyses, however, fail to correct for serial correlation. In this paper, evidence is presented to show that ignoring multiple serial correlation can have important policy implications. Based on monthly time series data from the Indianapolis Public Transit Corporation, the results indicate that failure to correct for serial correlation significantly affects economies of capital utilization estimates and has potentially important implications for optimal size of the transit fleet.