NEGATIVE BINOMIAL ANALYSIS OF INTERSECTION-ACCIDENT FREQUENCIES

Traffic accidents at urban intersections result in a huge cost to soci ety in terms of death, injury, lost productivity, and property damage. Unfortunately, the elements that effect the frequency of intersection accidents are not well understood and, as a result, it is difficult t o predict the effectiveness of specific intersection improvements that are aimed at reducing accident frequency. Using seven-yr accident his tories from 63 intersections in Bellevue, Washington (all of which wer e targeted for operational improvements), this paper estimates a negat ive binomial regression of the frequency of accidents at intersection approaches. The estimation results uncover important interactions betw een geometric and traffic-related elements and accident frequencies. T he findings of this paper provide exploratory methodological and empir ical evidence that could lead to an approach to estimate the accident reduction benefits of various proposed improvements on operationally d eficient intersections.