Kim Hong Sok, Kim Hyung Jin, Son Bongsoo
Department of Urban Planning and Engineering, Yonsei University, 134 Shinchon-dong, Seodaemun-gu, Seoul 120-749, South Korea.
Accid Anal Prev. 2006 Sep;38(5):981-7. doi: 10.1016/j.aap.2006.04.001. Epub 2006 May 11.
This paper develops an econometric model for vehicles' inherent mortality rate and estimates the probability of accidents and survival in the United States. Logistic regression model is used to estimate probability of survival, and censored regression model is used to estimate probability of accidents. The estimation results indicated that the probability of accident and survival are influenced by the physical characteristics of the vehicles involved in the accident, and by the characteristics of the driver and the occupants. Using restrain system and riding in heavy vehicle increased the survival rate. Middle-aged drivers are less susceptible to involve in an accident, and surprisingly, female drivers are more likely to have an accident than male drivers. Riding in powerful vehicles (high horsepower) and driving late night increase the probability of accident. Overall, the driving behavior and characteristics of vehicle does matter and affects the probabilities of having a fatal accident for different types of vehicles.
本文建立了一个关于车辆固有死亡率的计量经济模型，并估算了美国交通事故及存活的概率。采用逻辑回归模型估算存活概率，采用删失回归模型估算事故概率。估计结果表明，事故及存活概率受事故所涉车辆的物理特性、驾驶员及乘客特征的影响。使用约束系统以及乘坐重型车辆可提高存活率。中年驾驶员发生事故的可能性较小，令人惊讶的是，女性驾驶员比男性驾驶员更易发生事故。驾驶大功率车辆（高马力）以及深夜驾驶会增加事故概率。总体而言，驾驶行为及车辆特性确实重要，并会影响不同类型车辆发生致命事故的概率。
