Effects of Roadway Geometric Design Features on Frequency of Truck-Related Crashes

Abstract

Because truck-related crashes are a socioeconomic concern that can result in tremendous loss of life and property, unbiased, relatively accurate estimations of crash frequency are essential. A data set from Tennessee was used to examine the effects of roadway geometric design features and other relevant attributes on the frequency of truck-related crashes. Negative binomial (NB) and zero-inflated NB (ZINB) models were proposed to identify the risk factors that had significant effects on the frequency of crashes that involved large trucks. Differences in truck-related crashes were investigated across collision vehicle types, and three crash count models—total truck related, car–truck, and truck only—were developed under the ZINB and NB frameworks. Elasticities were estimated for these crash count models to identify the most critical variables contributing to crashes. Findings suggest that the ZINB models have most of the desirable statistical properties (i.e., better goodness of fit and more significant variables identified). Model results revealed seven factors significant for the frequency of truck-related crashes regardless of crash type: annual average daily traffic, percentage of trucks, segment length, degree of horizontal curvature, terrain type, median type, and posted speed limit. Results of elasticity estimation reveal that the percentage of trucks is the most critical variable of all explanatory variables for the frequency of truck-related crashes.