Empirical Insights on Improving Bus Reliability at a Rural Transit System

Using a comprehensive data set, we investigate the impact of drivers, vehicles, trips, months, and days of the work week on deviation of actual run time from scheduled run time. Our results provide insights into what makes a bus service more reliable by analyzing the year-long data set from Butler Transit Authority, Pennsylvania, which is a rural system. The multiple regression methodology we employ reduces omitted variables bias so that each included explanatory variable’s coefficient estimate is relatively free from bias compared to more simplistic econometric methods such as correlation or bivariate regression. We find that problem drivers, lunch hour and afternoon peak times, November, and Fridays, are the variables that reduce bus reliability the most. Our study speaks to the critical need for information-intensive design and delivery of reliable bus service. Analyses of such databases help the public, in general, and the transit authorities, in particular, in providing efficient and effective bus service systems.