Recent research has advocated the use of linear intervention models developed within a hierarchical full Bayes context to conduct road safety evaluations. These models acknowledge that the effects of a safety treatment (intervention) do not occur instantaneously but are spread over future time periods. Despite the demonstrated advantages of such models, the manner in which the implemented countermeasures affect safety at the treated locations according to their novelty, direct effects, and indirect effects is not completely understood. A novel nonlinear intervention model was proposed to better understand how safety countermeasures work. To demonstrate the proposed model's capabilities, linear and nonlinear (Koyck) models were applied to estimate the effectiveness of the installation of shoulder rumble strips on a number of highway segments in the province of British Columbia, Canada. In addition to providing the best fit, the nonlinear Koyck model provided valuable insight into the effectiveness of shoulder rumble strips. This model showed an immediate 24.9% reduction of off-road-right collisions after 1 year that decreased with time and a 19.2% reduction in collisions as a result of permanent treatment. Overall, the findings from this study can have a significant impact on the economic evaluation of safety programs and countermeasures.
Linear and Nonlinear Safety Intervention Models
Novel Methods Applied to Evaluation of Shoulder Rumble Strips
Transportation Research Record
Transportation Research Record: Journal of the Transportation Research Board ; 2280 , 1 ; 28-37
2012-01-01
Article (Journal)
Electronic Resource
English
Transportation Research Record | 2012
|From Nonlinear Physical Models to Linear Models
Springer Verlag | 2023
|