Assessing the safety effect of red-light camera deactivation: a geographically weighted negative binomial regression approach

Abstract Municipalities across the country have debated safety effect of automatic red-light cameras (RLC) and their political financial implications. Most empirical studies used Empirical Bayesian (EB) approach to assess safe effects facilitate policy debates. While popular, EB method has several limitations in data requirement, reference site selection, control confounding factors. Moreover, RLC deactivation are limited. This study fills these gaps using Moran’s I statistic Geographically Weighted Negative Binomial Regression (GWNBR) for City Arlington, Texas. The results indicate that total, injury, angle crashes Arlington on rise over period higher at intersections than those other intersections. direct removing RLCs is statistically significant. spillover observed but insignificant. Speed limit plays an important role road safety. findings significant implications research practices.