Modeling driver behavior in dilemma zones: A discrete/continuous formulation with selectivity bias corrections

• We examine the factors influencing driver behavior in dilemma zones Type I and II.
• Driver behavior was modeled using a two-step mixed logit/mixed regression technique.
• Both selectivity bias and unobserved heterogeneity were found significant.
• Young, old, and female drivers were found to have larger rates of acceleration.
• Cell phone usage impacts on driver behavior were found significant but highly variable.

The evaluation of driver behavior in dilemma zones is of critical importance to traffic safety and intersection design, but has thus far received limited investigation. Internal and external factors that can influence this behavior include driver demographics, the use of technology in the vehicle, and even the type of dilemma zone—Type I (based on signal timing/intersection geometry) or Type II (based on driver indecision). This paper explores the effect of cell phone technology, calling behavior, and driver characteristics on drivers' decisions to stop or go through an intersection at the onset of a yellow light, along with their corresponding rate of acceleration. A discrete/continuous analysis was adopted that accounted for potential model heterogeneity that may exist across the different dilemma zone types and drivers by applying selectivity-bias corrections. The results suggested that several technology and call behavior combinations are relevant in determining driver behavior, along with gender and age. It was also found that significant differences exist in driver behavior amongst those who decide to stop and those who decide to go through the intersection in a Type II dilemma zone situation. The findings of this paper can support efforts on reducing risky driving behavior in dilemma zones and enforcing distracted driving laws.