Prioritizing highway safety improvement projects: A Monte-Carlo based Data Envelopment Analysis approach.

Abstract

Road authorities have to prioritize safety improvement projects due to budget limitations. This process needs to estimate expected benefits (reduction in average crash frequency) and costs of projects. Due to variances of crash modification factor (CMF), crash frequency and cost of projects, prediction of costs and benefits would be accompanied by uncertainty and it can subsequently lead to a wrong decision making. To deal with the inherent uncertainty in the decision making process, this paper presents a ranking approach based on integration of Data Envelopment Analysis and Monte-Carlo simulation. A Monte-Carlo simulation is applied to generate stochastic values as input and outputs of the problem instead of running DEA model just for deterministic case. Data from an existing case study is used to evaluate the performance of the proposed methodology. Numerical results indicate that DEA results are very sensitive to data uncertainty and uncertainties can have great influence in ranking results of road safety improvement projects especially when both input and output data are uncertain. It also indicates that how the proposed methodology can be useful for detecting sensitive decision-making units and providing a more comprehensive view for decision makers to allocate a limit budget to the most efficient safety improvement projects.