This paper presents a case study carried out in multiple cities of the Valencian Community (Spain) to determine the effect of sociodemographic and road characteristics on traffic accident risk. The analyzes are performed at the road segment level, considering the linear network representing the road structure of each city as a spatial lattice. The number of accidents observed in each road segment from 2010 to 2019 is taken as the response variable, and a zero-inflated modeling approach is considered. Count overdispersion and spatial dependence are also accounted for. Despite the complexity and sparsity of the data, the fitted models performed considerably well, with few exceptions. The results show that the effect of most of the covariates is highly heterogeneous across cities. In particular, the impact of roundabouts and main roads on accident risk is overall consistent across the cities studied, whereas the role of sociodemography and other road features seems much more uncertain. Furthermore, the distribution of zeros and non-zeros displays a markedly spatial structure, whereas the magnitude of non-zeros is generally unstructured in space. These findings could be useful to establish preventive measures at the street level in the future.

本文介绍了在巴伦西亚自治区（西班牙）多个城市进行的案例研究，以确定社会人口统计学和道路特征对交通事故风险的影响。考虑将代表每个城市道路结构的线性网络表示为空间格，在路段一级进行分析。将2010年至2019年在每个路段观察到的事故数量作为响应变量，并考虑采用零膨胀建模方法。还考虑了计数过度分散和空间依赖性。尽管数据复杂且稀疏，但拟合模型仍然表现出色，几乎没有例外。结果表明，大多数协变量的影响在城市之间是高度异质的。尤其是，在所研究的城市中，回旋处和主要道路对事故风险的影响总体上是一致的，而社会人口统计学和其他道路特征的作用似乎更加不确定。此外，零和非零的分布显示出明显的空间结构，而非零的大小通常在空间中是非结构化的。这些发现可能对将来在街道上建立预防措施很有用。