Modeling temporal correlation and heterogeneity in real-time conflict rates using Bayesian Tobit models for signalized intersections.

The use of real-time traffic conflicts for safety studies provide more insight into how important dynamic signal cycle-related characteristics can affect intersection safety. However, such short-time window for data collection raises a critical issue that the observed conflicts are temporally correlated. As well, there is likely unobserved heterogeneity across different sites that exist in conflict data. The objective of this study is to develop real-time traffic conflict rates models simultaneously accommodating temporal correlation and unobserved heterogeneity across observations. Signal cycle level traffic data, including traffic conflicts, traffic and shock wave characteristics, collected from six signalized intersections were used. Three types of Tobit models: conventional Tobit model, temporal Tobit (T-Tobit) model, and temporal grouped random parameters (TGRP-Tobit) model were developed under full Bayesian framework. The results show that significant temporal correlations are found in T-Tobit models and TGRP-Tobit models, and the inclusion of temporal correlation considerably improves the goodness-of-fit of these Tobit models. The TGRP-Tobit models perform best with the lowest Deviance Information Criteria (DIC), indicating that accounting for the unobserved heterogeneity can further improve the model fit. The parameter estimates show that real-time traffic conflict rates are significantly associated with traffic volume, shock wave area, shock wave speed, queue length, and platoon ratio.

Evaluation of driver demand for in-vehicle information: An integrated method combining clustering and multivariate ordered probit model.

INTRODUCTION: The proper execution of driving tasks requires information support. While new technologies have increased the convenience of information access, they have also increased the risk of driver distraction and information overload. Meeting drivers' demands and providing them with adequate information are crucial to driving safety. METHODS: Based on a sample of 1,060 questionnaires, research on driving information demands is conducted from the perspective of drivers. A principal component analysis and the entropy method are integrated to quantify the driving information demands and preferences of drivers. The K-means classification algorithm is selected to classify the different types of driving information demands, including dynamic traffic information demands (DTIDs), static traffic information demands (STIDs), automotive driving status information demands (ATIDs), and total driving information demands (TDIDs). Fisher's least significant difference (LSD) is used to compare the differences in the numbers of self-reported crashes among different driving information demand levels. A multivariate ordered probit model is established to explore the potential factors that influence the different types of driving information demand levels. RESULTS: The DTID is the driver's most in-demand information type, and accordingly, gender, driving experience, average driving mileage, driving skills, and driving style significantly affect the driving information demand levels. Moreover, the number of self-reported crashes decreased as the DTID, ATID, and TDID levels decreased. CONCLUSION: Driving information demands are affected by a variety of factors. This study also provides evidence that drivers who have higher driving information demands are more likely to drive more carefully and safely than their counterparts who do not exhibit high driving information demands. PRACTICAL IMPLICATIONS: The results are indicative of the driver-oriented design of in-vehicle information systems and the development of dynamic information services as a way to avoid negative impacts on driving.