Combined Prediction Model of Death Toll for Road Traffic Accidents Based on Independent and Dependent Variables

Abstract

In order to build a combined model which can meet the variation rule of death toll data for road traffic accidents and can reflect the influence of multiple factors on traffic accidents and improve prediction accuracy for accidents, the Verhulst model was built based on the number of death tolls for road traffic accidents in China from 2002 to 2011; and car ownership, population, GDP, highway freight volume, highway passenger transportation volume, and highway mileage were chosen as the factors to build the death toll multivariate linear regression model. Then the two models were combined to be a combined prediction model which has weight coefficient. Shapley value method was applied to calculate the weight coefficient by assessing contributions. Finally, the combined model was used to recalculate the number of death tolls from 2002 to 2011, and the combined model was compared with the Verhulst and multivariate linear regression models. The results showed that the new model could not only characterize the death toll data characteristics but also quantify the degree of influence to the death toll by each influencing factor and had high accuracy as well as strong practicability.

Road traffic injuries in China from 2007 to 2016: the epidemiological characteristics, trends and influencing factors

“…Moreover, the dramatic increased in vehicle ownership over the past few years has resulted in an increase in traffic accidents. A previous study also showed road traffic injury mortality appeared to be statistically related to GDP, motorization, population and car ownership (Feng et al, 2014). This study also found that with the increase of the number of health institutions, death tolls showed a downward trend.…”

“…We found that GDP-per-capita, education level, the number of health institutions, population, and car ownership status had significant correlations with traffic death tolls, which also indicated that the regression model fit the data very well. Previous studies also reported that GDP-per-capita had a significant correlation with traffic death tolls (Feng et al, 2014; Bougueroua & Carnis, 2016; Tan et al., 2014a; Tan et al., 2014b). Education level and the number of vehicles involved in the accident strongly affected the non-occurrence rate of traffic accidents, which was similar to this study’s results (Tan et al., 2014a; Tan et al., 2014b Oralhan & Goktolga, 2018).…”

“…Moreover, the results suggest that reduced economic activity has been a beneficial impact on traffic fatalities (Bougueroua & Carnis, 2016; Noland & Zhou, 2017). Many road traffic crashes in low- and middle-income countries, where urbanization and motorization are rapidly increasing, may be due to the growing number of motor vehicles on the road (Feng et al, 2014). The Eastern region of China maintains the highest economic growth rates and the number of car ownership registrations was 5,480.71 million during 2007–2016.…”

“…In 2009, road traffic deaths accounted for about 70,000 premature deaths in China and road traffic accidents disproportionately affected the following populations: males, persons 21–65 years old, adults aged more than 65 years, persons living in rural areas, pedestrians, passengers, motorcyclists and bicyclists (Zhang et al, 2013). Rapid economic growth and intensive motorization accompanied rising rates of traffic fatalities (Blumenberg et al, 2017; Feng et al, 2014), and one of the main factors contributing to traffic fatalities is the growing number of motor vehicle. It is estimated that about 55 thousand new motor vehicles are registered in China every day.…”

A Spatial Analysis Methodology Based on Lazy Ensembled Adaptive Associative Classifier and GIS For Examining the Influential Factors on Traffic Fatalities

“…The first group of methods bases on multivariate regression. For example, Feng et al [6] combined Verhulst and multivariate linear regression models to analyze the fatalities of road traffic accidents in China from 2002 to 2011; Girotto et al [2] investigated the relationship between professional experience and traffic accidents or near-miss accidents among truck drivers using multinomial logistic regression. Anastasopoulos et al [3] used the multivariate Tobit regression model to analyze the highway accident-injuryseverity rates.…”