School of Civil Engineering, Qingdao University of Technology, Qingdao 266520, China; Engineering Research Center of Concrete Technology under Marine Environment, Ministry of Education, Qingdao 266520, China.
School of Transportation, Jilin University, Changchun 130012, China.
Accid Anal Prev. 2024 Dec;208:107805. doi: 10.1016/j.aap.2024.107805. Epub 2024 Oct 4.
Highway crashes are responsible for a significant number of severe and fatal injuries drawing considerable attention from transportation authorities and safety researchers. This paper aims to investigate the unobserved heterogeneous effects of various risk factors, such as pre-crash circumstances, environmental and road conditions, vehicle-involved information, and driver attributes on injury severities. Our methodology uses a hybrid approach that combines two-step cluster analysis and latent class ordered regression model with covariates. The proposed approach extends traditional latent class model by elucidating potential relationships among predictors, covariates, and outcomes. A cross-sectional crash data covering a period of over five years (2011-2016) was obtained via the Dutch crash registration database for modeling injury severity outcomes. The results reveal substantial and statistically significant differences in injury severity between two latent classes. Moreover, we identify road lighting, time of crash, road surface conditions, weather, and season as covariates influencing class membership prediction. Factors such as high speed, alcohol involvement, frontal collision points, and older driver demographics increase the probability of serious injury and facility across all cases analyzed. Additionally, we observe notable heterogeneity effects between the two classes regarding temporal characteristics, the number and type of vehicles involved, as well as driver gender. Our findings provide specific and valuable insights into injury severity outcomes, which can inform the formulation of targeted safety countermeasures and regulatory strategies for traffic policies and relevant agencies.
公路交通事故是造成严重和致命伤害的主要原因，引起了交通管理部门和安全研究人员的高度关注。本文旨在研究各种风险因素（如事故前情况、环境和道路条件、涉事车辆信息和驾驶员特征）对伤害严重程度的未观察到的异质影响。我们的方法采用了两步聚类分析和带有协变量的潜在类别有序回归模型的混合方法。该方法通过阐明预测因素、协变量和结果之间的潜在关系，扩展了传统的潜在类别模型。通过荷兰碰撞登记数据库获得了涵盖五年以上（2011-2016 年）时间段的横截面碰撞数据，用于建模伤害严重程度结果。结果表明，两个潜在类别之间在伤害严重程度上存在显著且具有统计学意义的差异。此外，我们确定了道路照明、碰撞时间、路面状况、天气和季节等协变量会影响类别成员的预测。高速度、酒精参与、正面碰撞点和老年驾驶员等因素增加了所有分析案例中严重伤害和设施的可能性。此外，我们还观察到两个类别之间在时间特征、涉及车辆的数量和类型以及驾驶员性别方面存在显著的异质效应。我们的研究结果为伤害严重程度的结果提供了具体而有价值的见解，可以为交通政策和相关机构的安全对策和监管策略的制定提供信息。
