Investigation of surrogate measures for safety assessment of urban two-way stop controlled intersections

Crash prediction models used to estimate safety of highway segments and intersections are traditionally developed using various traffic volume measures. There are issues with this approach and surrogate safety measures such as conflicts and delays have been proposed to overcome them. This study investigates the statistical relationships between crash frequencies and traffic volume, intersection delay, and simulated conflicts to explore and compare the viability of these models for estimating safety at urban two-way stop controlled intersections. The database used includes 78 three leg and 55 four leg intersections within the city of Toronto, Canada. Crash prediction models were developed and evaluated based on various goodness-of-fit measures. With the developed models, an alternate approach to crash based evaluations of intersection improvements is presented. A case study is developed to investigate and demonstrate the use of the models for estimating the safety impact of implementing a left turn lane on a major approach of an urban three leg stop controlled intersection. This case study and other results confirm the promise of the approach, suggesting that surrogate measures, such as the ones investigated, can capture effects of factors other than traffic volume alone.