Applying Structural Equation Modeling to Public Transit Supply and Demand

• Activity Number: 376
• Type: Contributed
• Date/Time: Tuesday, August 11, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Transportation Statistics Interest Group
• Author(s): John Handley*
• Companies: Xerox Corporation
• Keywords: transportation ; planning ; Bayesian modeling ; JAGS

Abstract

The relationship between scheduled capacity and concomitant demand in transit is of fundamental interest to transit planners. The expectation is that offered capacity in terms of more frequent service and more bus stops is consumed by customers. Thus relationship has been modeled at an aggregate level for whole transit agencies across regions but not at the operational level. This work studies the statistical relationships among operational capacity, demand and revenue using a year's worth of day-by-day trip-level data over 29 routes of a public transit system. Structural equation modeling is used to account for groups of collinear observational variables to identify and link three latent constructs, revenue capacity, demand, and productivity. We find that the endogenous variables revenue capacity and demand are positively, but weakly linked, showing that increased scheduled capacity is used. Yet there are variations route by route and those variations have no obvious relationship to route function (cross-town inner city versus suburban commuting).