Leading pedestrian intervals – Yay or Nay? A Before-After evaluation of multiple conflict types using an enhanced Non-Stationary framework integrating quantile regression into Bayesian hierarchical extreme value analysis

•A non-stationary framework for before-after analysis combining Bayesian Hierarchical Extreme Value analysis with Quantile Regression.•Traffic conflicts were extracted by artificial intelligence-based advanced video analytics before and after the Leading Pedestrian Interval (LPI) treatment.•Estimated conflict thresholds used with the non-stationary Bayesian Hierarchical Peak-Over Threshold model to estimate crash risk.•Odds Ratio analysis suggests that LPI treatment reduced vehicle–pedestrian crash risks.•The LPI treatment does not increase rear-end crash risk.