Using random-parameter and fixed-parameter ordered models to explore temporal stability in factors affecting drivers' injury severity in single-vehicle collisions

Understanding the temporal stability in the factors influencing drivers' injury severity in single-vehicle collisions would help evaluating the effectiveness of implementing different safety treatments so that researchers could understand whether any safety improvements, observed after applying a certain safety treatment, are attributed to the specific treatment or simply attributed to the temporal instability of the factors being addressed. This study investigates the temporal stability of the factors affecting drivers' injury severity in single-vehicle collisions involving light-duty vehicles. The study is based on utilizing ordinal regression modeling to analyze the severity of drivers' injuries in all police-reported light-duty single-vehicle collisions that occurred in North Carolina from January 1, 2007, to December 31, 2013. A separate regression model was estimated for each year so that statistical significance of each risk factor may be compared over the years. The study also estimated random-parameter (mixed) ordered logit models to explore the heterogeneity in data. The most significant factor that was found to increase the severity of drivers' injuries in light-duty single-vehicle collisions is driving under the influence of alcohol or illicit drugs. Other significant factors, in decreasing order in terms of their significance, include driving on a highway curve, exceeding speed limit, lighting conditions, the age of the driver, and the age of the vehicle. In contrast, there were six factors that were found to be significant in only some years and not in all years. These six temporally unstable factors include the use of seatbelt, driver's gender, rural highways, undivided highways, the type of the light-duty vehicle, and weather and road surface conditions. These same factors were found by other previous research studies to be significant and stable predictors of drivers' injury severity in single-vehicle collisions.