Crash injury severity analysis using a two-layer Stacking framework

Tang, Jinjun; Liang, Junbin; Han, Chunyang; Li, Zhibin; Huang, Helai

doi:10.1016/j.aap.2018.10.016

Cited by 185 publications

(83 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The exclusive use of quantitative methods (specifically statistical modelling) to analyze risk factors suffers from several weaknesses when applied to injury studies. A reliance on large sample sizes/populations to achieve adequate statistical power biases studies of smaller locales towards the null hypothesis, almost certainly leading to important patterns and risk factors being rejected due to inadequate statistical significance [6][7][8][9]. A traditional hypothesis testing (or otherwise p-value or confidence-interval-focused) approach additionally relies on assumptions of underlying distributions to assume multiple samples from a consistent population (a particularly perilous problem when using geospatial models), which, well suited to inferential modelling of highly-controlled experimental conditions [10], falls short of accounting for the non-parametric nature of models.…”

Section: Mixed Methodsmentioning

confidence: 99%

Qualitative Field Observation of Pedestrian Injury Hotspots: A Mixed-Methods Approach for Developing Built- and Socioeconomic-Environmental Risk Signatures

Schuurman

Walker

Swanlund

et al. 2020

IJERPH

View full text Add to dashboard Cite

Road traffic injuries constitute a significant global health burden; the World Health Organization estimates that they result in 1.35 million deaths annually. While most pedestrian injury studies rely predominantly on statistical modelling, this paper argues for a mixed-methods approach combining spatial analysis, environmental scans, and local knowledge for assessing environmental risk factors. Using data from the Nova Scotia Trauma Registry, severe pedestrian injury cases and ten corresponding hotspots were mapped across the Halifax Regional Municipality. Using qualitative observation, quantitative environmental scans, and a socioeconomic deprivation index, we assessed hotspots over three years to identify key social- and built-environmental correlates. Injuries occurred in a range of settings; however, clear patterns were not observed based on land use, age, or socio-economic status (SES) alone. Three hotspots revealed an association between elevated pedestrian injury and a pattern of geographic, environmental, and socio-economic factors: low- to middle-SES housing separated from a roadside attraction by several lanes of traffic, and blind hills/bends. An additional generalized scenario was constructed representing common risk factors across all hotspots. This study is unique in that it moves beyond individual measures (e.g., statistical, environmental scans, or geographic information systems (GIS) mapping) to combine all three methods toward identifying environmental features associated with pedestrian motor vehicle crashes (PMVC).

show abstract

Section: Mixed Methodsmentioning

confidence: 99%

Qualitative Field Observation of Pedestrian Injury Hotspots: A Mixed-Methods Approach for Developing Built- and Socioeconomic-Environmental Risk Signatures

Schuurman

Walker

Swanlund

et al. 2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…On the contrary, public transit, with uncertain waiting time and fixed routes, has a limitation to undertake multiple activities in a tour [21,22]. Therefore, the complex trip chains may increase the dependence of travelers on automobiles, which leads to the problems related to auto route choice and optimization, as well as transportation safety [23][24][25][26][27][28][29][30][31]. In order to verify this conclusion, this paper also takes the mode choice of commuters as one of the independent variables.…”

Section: Introductionmentioning

confidence: 94%

A Multivariate Modeling Analysis of Commuters’ Non-Work Activity Allocations in Xiaoshan District of Hangzhou, China

Guan

Shi

et al. 2019

Sustainability

View full text Add to dashboard Cite

This paper investigates the outdoor non-work activity allocation behaviors of commuters in Xiaoshan District of Hangzhou, China, as well as the underlying relationship among different types of outdoor non-work activities. As per their commute and work schedules, commuters' outdoor non-work activities are classified into six categories and considered as binary dependent variables for modeling analysis, including from home before work, on commute way from home to work, going home during work, going out (not going home) during work, on commute way from work back home, and from home after work. Independent variables include commute attributes, work schedules, sociodemographic attributes, and built-environmental attributes. A multivariate probit model is developed to explore the effects of explanatory variables and capture correlations among unobserved influential factors. The model estimation results show that daily work time, education years, and traffic zone have substantial impacts on commuters' non-work activity allocations. As for the underlying relationship among unobserved factors, a positive correlation is found between the outdoor non-work activities on commute way to and from work, indicating a mutually promotive relationship. All other correlations are negative, indicating other types of non-work activities are mutually substitutive. These findings will help to better understand commuters' behaviors of outdoor activity arrangement subject to the time-space constraint from fixed work schedules, and shed some light on the mechanism of complex work tour formation, so as to guide the development of activity-based travel demand models for commuters.

show abstract

“…Thus, machine learning methods with little or no prior hypothesis for input variables were introduced to identify risk factors. Examples include artificial neural networks (ANN) [22], boosted regression trees (BRT) [23], support vector machines (SVM) [24], and stacking of several machine learning methods [25]. The major disadvantage of machine learning methods is that they often lack a direct and clear interpretation between accident severity and related variables.…”

Section: Influence Factors On Traffic Accidentsmentioning

confidence: 99%

Geographical Detection of Traffic Accidents Spatial Stratified Heterogeneity and Influence Factors

Zhang

2020

IJERPH

View full text Add to dashboard Cite

The purpose of this paper is to investigate the existence of stratification heterogeneity in traffic accidents in Shenzhen, what factors influence the casualties, and the interaction of those factors. Geographical detection methods are used for the analysis of traffic accidents in Shenzhen. Results show that spatial stratification heterogeneity does exist, and the influencing factors of fatalities and injuries are different. The traffic accident causes and types of primary responsible party have a strong impact on fatalities and injuries, followed by zones and time interval. However, road factors, lighting, topography, etc., only have a certain impact on fatalities. Drunk driving, speeding over 50%, and overloading are more likely to cause more casualties than other illegal behaviors. Speeding over 50% and speeding below 50% have significant different influences on fatalities, while the influences on injuries are not obvious, and so do drunk driving (Blood Alcohol Concentration ≥ 0.08) and driving under the influence of alcohol (0.08 > Blood Alcohol Concentration ≥ 0.02). Both pedestrians and cyclists violating the traffic law are vulnerable to fatality. Heavy truck overloading is more likely to cause major traffic accidents than minibuses. More importantly, there are nonlinear enhanced interactions between the influencing factors, the combination of previous non-significant factors and other factors can have a significant impact on the traffic accident casualties. The findings could be helpful for making differentiated prevention and control measures for traffic accidents in Shenzhen and the method selection of subsequent research.

show abstract

Crash injury severity analysis using a two-layer Stacking framework

Cited by 185 publications

References 29 publications

Qualitative Field Observation of Pedestrian Injury Hotspots: A Mixed-Methods Approach for Developing Built- and Socioeconomic-Environmental Risk Signatures

Qualitative Field Observation of Pedestrian Injury Hotspots: A Mixed-Methods Approach for Developing Built- and Socioeconomic-Environmental Risk Signatures

A Multivariate Modeling Analysis of Commuters’ Non-Work Activity Allocations in Xiaoshan District of Hangzhou, China

Geographical Detection of Traffic Accidents Spatial Stratified Heterogeneity and Influence Factors

Contact Info

Product

Resources

About