Measuring Influence of Accessibility on Accident Severity with Structural Equation Modeling

Abstract

Structural equation modeling (SEM) is a confirmatory, multivariate technique used to examine causal relationships between variables. Related to path analysis with a goal of selecting a model that best explains underlying relationships between variables, SEM is a useful tool for traffic safety research. This study examined the severity of crashes in terms of factors commonly attributed to accidents. These factors included human, vehicle, and roadway factors, along with accessibility measures that were considered relevant in previous studies. In this study, SEM was used to test an a priori model of crash severity. The analysis was carried out in a two-step process. The measurement model was first tested with a confirmatory factor analysis. After the validity of the measurement model was established, a four-latent-factor structural model was run. With an acceptable model fit, the magnitude of standardized path coefficients from the exogenous latent variables provided a means to assess the relative importance of the latent factors on crash severity. The results showed that the human latent factor was the most influential. Although a positive statistical relationship existed between roadway factors and crash severity, accessibility factors had the opposite effect on crash severity, that is, increased accessibility was shown to reduce crash severity.