Statistical Versus Simulation Models in Safety: Steps Toward a Synthesis.

Rational planning involves selecting from among possible courses of action with regard to their predicted consequences. In road safety engineering,this requires being able to predict the frequency and/or severity of crashes that are expected to result from design or operational changes. The dominant approach used in the first edition of the Highway Safety Manual (HSM) to address this issue is statistical modeling, but we can expect that over time statistical models will be replaced by models which explicitly describe mechanisms underlying crash occurrence. This development could be accelerated if the already substantial investment in statistical safety models could be used to calibrate and/or validate mechanism-based simulation models. In this paper we first briefly review two efforts where statistical models of median-crossing crash frequency were developed. An objective of both statistical studies was to summarize how the expected frequency of median-crossing crashes (MCCs) varies with the average daily traffic and median width of a divided highway. After describing the nature of our simulation model we use these summarized relationships as criteria for assessing the performance of the simulation model.