Crash frequency and severity modeling using clustered data from Washington State

Abstract

This study investigates the relationship between crash frequencies, roadway design and use features by utilizing the benefits of clustered panel data. Homogeneous high-speed roadway segments across the State of Washington were grouped using cluster analysis technique, resulting in grouped observations with reasonably continuous crash count values. This permitted application of both fixed- and random-effects linear regression models for the total number of crashes 100 per million vehicle miles traveled (VMT). A crash severity model also was estimated, using an ordered probit regression, allowing transformation of total crash counts into counts by severity. Speed limit information is found to be very valuable in predicting crash occurrence. For roadways with average design and use attributes, a 10 mi/h increase speed limit from 55 mi/h results in 3.29% more crashes expected for the average roadway section at a speed limit of 55 mi/h. However, speed limits may have biased coefficients, most likely attributable to unobserved safety-related effects. In addition, the authors also conducted a cost/benefit analysis of raising speed limit. An increase in speed limit from 55 mi/h to 65 mi/h would save 106,879 hours per 100 million VMT, which is equivalent to $ 1,607,455. The additional crash counts due to the increase in speed limit only cause $ 437,964 loss. The results suggest that raising speed limits can offer some considerable time savings benefits