Institute of Transportation, MOTC

       Street intersection crashes often involve two parties (vehicle-vehicle and vehicle-pedestrian). The disregard for the right-of-way of motorcycles and the pedestrian environment in our country has been ignored, making vulnerable users more prone to serious accidents. However, existing improvement has been proven ineffective. Therefore, it is necessary to analyze the factors affecting the injury severity and to make improvements accordingly. The parties involved in crashes can vary considerably. To accurately identify the causality of a two-party crash, it is necessary to assess the damage of both parties simultaneously. While the latent class ordinal model has been used in crash severity studies to capture heterogeneity in crash propensity, most are univariate. They are inappropriate for the context of two-vehicle crashes. We propose a latent class parameterized correlation bivariate generalized ordered probit (LCp-BGOP) model to examine two-party crashes at intersections in the study.
       This study collected 32,308 cases of two-party crashes at street intersections in Taipei City from 2018 to 2020. Injury severity is categorized into three levels: property damage only, minor/possible injury, and fatal/evident injury. Here are two classes, low-risk and high-risk, determined as the optimal class number through the latent class method. The LCp-BGOP parameterizes the thresholds and within-crash correlations of two-party crash severity, and it classifies the crashes into distinct risk groups based on risk variables, thereby better understanding variables in intersection crashes. According to our model, the Ordinary Crash Severity (OCS) group mainly involves two-vehicle crashes colliding with motorcycles; the High Crash Severity (HCS) group comprises vulnerable road users like pedestrians and cyclists, mainly in mixed traffic with high volumes.
       Our model-based estimation points out several potential factors, such as drivers (elderly), violations (safety equipment, yielding to vehicles, or hit-and-run), and modes (four-wheeled vehicles, two-wheeled vehicles, or pedestrians). Three elements of traffic engineering, namely people, vehicles, and roads, are some existing risk factors that can influence severity. Through the elasticity effects, the OCS group has a higher magnitude of fatal/evident injury than the HCS does. By variable patterns, the mode of mobility exhibits the highest fatal/evident injury values, underscoring its significant influence. Accordingly, we hope to reduce violations at intersections and prevent large vehicle crashes.
       The results show that the party-specific factors contribute to injury severity more than generic factors do, providing invaluable insight into intersection crashes from the perspective of reducing two-party collisions. By integrating the traditional traffic 3E (Engineering, Education, and Enforcement) with Encouragement into 4E, we develop the corresponding safety measures to reduce the frequency and severity of future crashes. It is recommended that authorities implement the strategies proposed in this study and enhance public awareness of driving. Finally, this study clarifies causal relationships in accidents by analyzing crash severity and fault determination, enabling risk management for insurance.