TRB Paper 10-2563 Hot Spot Identification by Modeling Single-Vehicle and Multi-Vehicle Crashes Separately

There has been considerable research conducted on the development of statistical models for predicting motor vehicle crashes on highway facilities. These models have often been employed to estimate the number of crashes per unit of time for an entire highway segment or intersection, without distinguishing the influence different sub-groups have on crash risk. The two most important sub-groups that have been identified in the literature are singleand multi-vehicle crashes. Recently, some researchers have noted that developing two distinct models for these two categories of crashes provides better predicting performance than developing models combining both crash categories together for predicting crashes for an entire facility. Thus, the objective of this study is to determine whether there exists any difference in the identification of hotspots when a single model is applied rather than two distinct models. A hotspot (or blackspot) is a site that has an accident frequency which is significantly higher than expected at some prescribed level of significance. The data used for the comparison analysis were collected on Texas multilane undivided highways for the years 1997-2001. This study shows that modeling singleand multi-vehicle crashes separately predicts slightly fewer false positives and negatives than modeling them together under a single aggregated model in the hotspot identification process. Thus, it is recommended to develop separate models for singleand multi-vehicle crashes for predicting crashes and for the identification of hot spots.