No abstract

Despite the evident spatial character of road crashes, limited research has been conducted in road safety analysis to account for spatial correlation; further, the practical consequences of this omission are largely unknown. The purpose of this research is to explore the effect of spatial correlation in models of road crash frequency at the segment level. Different segment neighboring structures are tested to establish the most appropriate one in the context of modeling crash frequency in road networks. A full Bayes hierarchical approach is used with conditional autoregressive effects for the spatial correlation terms. Analysis of crash, traffic, and roadway inventory data from a rural county in Pennsylvania indicates the importance of including spatial correlation in road crash models. The models with spatial correlation show significantly better fit to the data than the Poisson lognormal model with only heterogeneity. Parameters significantly different from zero included annual average daily traffic (AADT) and shoulder widths less than 4 ft and between 6 and 10 ft. In four models with spatial correlation, goodness of fit was improved compared with the model including only heterogeneity. More important yet is the potential of spatial correlation to reduce the bias associated with model misspecification, as shown by the change in the estimate of the AADT coefficient and other parameters.

Recent research has shown the importance of spatial correlation in road crash models. Because many different spatial correlation structures are possible, however, this study tested several segment neighboring structures to establish the most promising one to model crash frequency in road networks. A multilevel approach was also used to account for the spatial correlation between road segments of different functional types, which are usually analyzed separately. The study employed a full Bayes hierarchical approach with conditional autoregressive effects for the spatial correlation terms. Analyses of crash, traffic, and roadway inventory data from rural engineering districts in Pennsylvania and Washington affirmed the importance of spatial correlation in road crash models. Pure distance-based neighboring models (i.e., exponential decay) performed poorly compared with adjacency-based or distance order models. The results also suggest that spatial correlation is more important in distances of 1 mi or less. The inclusion of spatially correlated random effects significantly improved the precision of the estimates of the expected crash frequency for all segments by pooling strength from their neighbors and thus reducing their standard deviation. Results from Pennsylvania and Washington showed that spatial correlation substantially increased the random effects. There was a consistent indication that 70% to 90% of the variation explained by the random effects resulted from spatial correlation. This suggests that spatial models offer a significant advantage, since poor estimates that result from small sample sizes and low sample means are a frequent issue in highway safety analysis. Application of spatial correlation to the identification of sites with promise indicated that more sites were identified because of a reduction in the variance of the estimates, which would allow for greater confidence in the selection of sites for treatment.

Traditionally, highway safety analyses have used univariate Poisson or negative binomial distributions to model crash counts for different levels of crash severity. Because unobservables or omitted variables are shared across severity levels, however, crash counts are multivariate in nature. This research uses full Bayes multivariate Poisson lognormal models to estimate the expected crash frequency for different levels of crash severity and then compares those estimates to independent or univariate Poisson lognormal estimates. The multivariate Poisson log-normal model fits better than the univariate model and improves the precision in crash-frequency estimates. The covariances and correlations among crash severities are high (correlations range from 0.47 to 0.97), with the highest values found between contiguous severity levels. Considering this correlation between severity levels improves the precision of the expected number of crashes. The multivariate estimates are used with cost data from the Pennsylvania Department of Transportation to develop the expected crash cost (and excess expected cost) per segment, which is then used to rank sites for safety improvements. The multivariate-based top-ranked segments are found to have consistently higher costs and excess costs than the univariate estimates, which is due to higher multivariate estimates of fatalities and major injuries (due to the random effects parameter). These higher estimated frequencies, in turn, produce different rankings for the multivariate and independent models. The finding of a high correlation between contiguous severity levels is consistent with some of the literature, but additional tests of multivariate models are recommended. The improved precision has important implications for the identification of sites with promise (SWiPs), because one formulation includes the standard deviation of crash frequencies for similar sites as part of the assessment of SWiPs.