Detecting Unsafe Roadways with Spatial Statistics: Point Patterns and Geostatistical Models

Abstract

A detection scheme that uses classical and spatial statistics has been developed to identify roadways with the most severe safety needs. It is based on the null hypothesis that all roadways have the same crash risk, that is, all have the same nonfatal and fatal crash rates throughout the entire study region. Fatal and nonfatal crash rates, which are assumed to be randomly distributed as Poisson processes, are modeled with a marked homogeneous Poisson process model. Since the traffic exposures are typically unknown at the crash sites, they are predicted with a geostatistical model. Locations, where the null hypothesis is rejected, are safety treatment candidates. P-value risk rankings are used to identify locations with the most severe safety needs. The results from alternative analyses—one using vehicle miles traveled and another using population as measures of traffic exposure—are conducted and compared. The state of New Hampshire is used in a case study. The effects of analyzing areas with small traffic exposures, the so-called small-area estimation problem, and the aim to develop a data-driven detection scheme that meets the requirements as an objective decision-making tool are discussed.