查看文章

This study investigates the injury severity of drivers involved in two-vehicle crashes in Toyota City, Japan. An ordered probit model is proposed to measure the injury severity of two drivers in two-vehicle crashes, which is supposed to be independent for drivers from the same accident. The Gibbs Sampler algorithm is implemented to estimate unknown parameters in the proposed model. The major findings suggest: 1) that crashes occurring at night are more prone to high injury severity, compared to other time-periods; 2) that the collision types like head-on, crossing and right-turn cause higher injury severity of drivers, compared to rear-end collision; 3) that trucks are much stronger and have more resistance to two-vehicle crashes compared to passenger cars; 4) that drivers aged less than 25 and greater than or equal to 70 are less likely to be seriously injured in two-vehicle crashes, compared to drivers aged between 25 and 69.