A new framework for modelling traffic conflict interval time based on correlated random parameter duration model with heterogeneity in means and variances
Accident Analysis & Prevention · 2026-01 · 224 · 108282
DOI: 10.1016/j.aap.2025.108282 ↗Kurz gefasst
Fachartikel in der Zeitschrift Accident Analysis & Prevention, 2026-01. Verfasst von Gen Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing, 210037, China. Electronic address: ligen@njfu.edu.cn. Hauptthemen laut MEDLINE: Accidents, Traffic, Automobile Driving, Models, Statistical. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China, Major Project of Philosophy and Social Science Research in Colleges and Universities of Jiangsu Province.
Abstract (Originalsprache)
Traffic conflict interval time on highways not only impacts traffic flow stability, heightens the risk of secondary conflicts, and adds uncertainty. To explore the impact of various factors on conflict interval time, this study proposes the correlated random parameters accelerated failure time (AFT) model with heterogeneity in means and variances (CRPHMV), aiming to uncover the correlations and heterogeneity among influencing factors. Given the High D trajectory data, the CRPHMV AFT model demonstrates superior fitting performance compared to other advanced models. Specifically, four variables-mean speed, acceleration variance, traffic flow, and high-risk conflicts exhibit heterogeneity effects. Further analysis reveals that the mean heterogeneity of medium-risk conflictsversus acceleration variance indicators, and vehicle type versus acceleration variance indicators, tends to shorten the conflict interval time, while the mean heterogeneity of speed difference between lanes versus acceleration variance indicators is associated with an increase in the conflict interval time. Interaction effects between the unobserved heterogeneity of mean speed and high-risk conflicts indicators, as well as, mean speed and acceleration variance indicators, were found to significantly impact conflict interval time. These research findings can provide valuable insights for traffic management authorities to further enhance road safety and make informed decisions regarding traffic control measures and regulations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing, 210037, China. Electronic address: ligen@njfu.edu.cn.
- College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing, 210037, China. Electronic address: xushengji@njfu.edu.cn.
- College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing, 210037, China. Electronic address: cwr@njfu.edu.cn.
- College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing, 210037, China. Electronic address: wwy@njfu.edu.cn.
- College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing, 210037, China. Electronic address: yanxuyichen@njfu.edu.cn.
- College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing, 210037, China. Electronic address: zyang_2016@163.com.
Förderung
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China
- Major Project of Philosophy and Social Science Research in Colleges and Universities of Jiangsu Province
- Natural Science Foundation of Beijing Municipality
Zitieren
APA
Li, G., Ji, S., Cheng, W., Wang, W., Yan, X., Yang, Z., Yang, Y., & Zhang, J. (2026). A new framework for modelling traffic conflict interval time based on correlated random parameter duration model with heterogeneity in means and variances. Accident Analysis & Prevention, 224, 108282. https://doi.org/10.1016/j.aap.2025.108282
Vancouver
Li G, Ji S, Cheng W, Wang W, Yan X, Yang Z, et al. A new framework for modelling traffic conflict interval time based on correlated random parameter duration model with heterogeneity in means and variances. Accident Analysis & Prevention. 2026;224:108282. doi:10.1016/j.aap.2025.108282
BibTeX
@article{Li2026,
author = {Li, Gen and Ji, Shengxu and Cheng, Wanrong and Wang, Weiyun and Yan, Xuyichen and Yang, Zhen and Yang, Yang and Zhang, Jie},
title = {A new framework for modelling traffic conflict interval time based on correlated random parameter duration model with heterogeneity in means and variances},
journal = {Accident Analysis & Prevention},
year = {2026},
volume = {224},
pages = {108282},
doi = {10.1016/j.aap.2025.108282}
}
EUVIMED