How is driving volatility related to intersection safety? A Bayesian heterogeneity-based analysis of instrumented vehicles data

•New concept of intersection-specific driving volatility for proactive safety management.•Rigorous data analytics methodology to analyze driving data from real-world connected vehicles test-bed.•Presents full Bayesian estimation via Markov Chain Monte Carlo (MCMC) based Gibbs sampling.•Vehicular speed, acceleration/deceleration, and vehicular jerk-based volatility measures are proposed.•Integrates connected vehicles, safety and traffic data to identify locations where crashes are waiting to happen.