A Spatial Statistics Methodology for Inspector Allocation Against Fare Evasion

This article discusses public transport fare evasion from the point of view of the relations between inspection actions and detected evasion, with the aim of improving the efficacy of the former. By applying spatial statistics methods to a large dataset from Lisbon, Portugal, namely, entropy-based local bivariate relationships (LBR) and geographically weighted regression (GWR), it is shown that the two variables are associated in a widespread manner throughout the city, mostly in a linear way. Mapping out marginal gains from inspection actions then shows where they detect the most evaders, allowing transport companies to relocate their inspector teams in a more effective manner. Results for Lisbon show that gains in effectiveness of circa 50% can be obtained, mostly by moving some inspector teams from the centre of the city to the periphery during daytime. The methodology requires only inspection/detection databases, which transport companies usually have, making it a valuable, practical tool to combat fare evasion.