A Robust and Distribution-Fitting-Free Estimation Approach of Travel Time Percentile Function based on L-moments

Travel time is one of the key indicators monitored by intelligent transportation systems, helping the systems to gain real-time insights into traffic situations, predict congestion, and identify network bottlenecks. Travel time exhibits variability, and thus suitable probability distributions are necessary to accurately capture full information of travel time variability. Considering the potential issues of insufficient sample size and the disturbance of outliers in actual observations, as well as the heterogeneity of travel time distributions, we propose a robust and distribution-fitting-free estimation approach of travel time percentile function using L-moments based Normal-Polynomial Transformation. We examine the proposed approach from perspectives of validity, robustness, and stability based on both theoretical probability distributions and real data. The results indicate that the proposed approach exhibits high estimation validity, accuracy and low volatility in dealing with outliers, even in scenarios with small sample sizes.