Traffic Signal Noncompliance at Urban Intersections: Cycle-Level Evidence and Uncertainty-Aware Site Prioritization for Smart Urban Mobility in Ecuador

Abstract

Traffic signal noncompliance at urban intersections remains a road-safety and traffic-management challenge, particularly where local monitoring and empirical evidence are limited. This study characterized yellow- and red-phase stop-line crossing events at eight signalized intersections in six Ecuadorian cities and developed a preliminary site-prioritization approach. After conservative quality control, 4126 traffic-signal cycles were aggregated into 69 observation blocks. Descriptive indicators, nonparametric comparisons, Poisson and negative binomial count models, residual diagnostics, seven sensitivity analyses, and bootstrap-based prioritization were applied. The analytical sample included 38,615 vehicles and 7069 stop-line crossing events, yielding an aggregate event rate of 18.31%. Red-phase crossings represented 70.41% of recorded events and yellow-phase crossings 29.59%, with substantial variation among sampled intersections. Yellow-phase crossings were treated as protocol-defined behavioral classifications rather than event-specific legal determinations. The selected NB1 model showed no evidence of an adjusted association between off-peak and peak periods (IRR = 0.994; 95% CI 0.918–1.076), and this result remained stable across all seven sensitivity analyses. The workflow provides a reproducible basis for site-specific assessment and uncertainty-aware screening. However, the findings are not representative city-wide estimates, and the prioritization score is an exploratory within-sample tool that does not independently justify specific interventions.