No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Risk factors associated with bus accident severity in the United States: A generalized logit model
Abstract
Recent years have witnessed a growing interest in improving bus safety operations worldwide. While in the United States buses are considered relatively safe, the number of bus accidents is far from being negligible, triggering the introduction of the Motor-coach Enhanced Safety Act of 2011.
The current study investigates the underlying risk factors of bus accident severity in the United States by estimating a generalized ordered logit model. Data for the analysis are retrieved from the General Estimates System (GES) database for the years 2005-2009.
Results show that accident severity increases: (i) for young bus drivers under the age of 25; (ii) for drivers beyond the age of 55, and most prominently for drivers over 65years old; (iii) for female drivers; (iv) for very high (over 65mph) and very low (under 20mph) speed limits; (v) at intersections; (vi) because of inattentive and risky driving.
... Over fifteen million people are wounded each year as a result of RTA's, according to WHO. . Jha et al. [9] Across the world, injuries account for around 5% of all deaths, most of which result from collisions with motor vehicles [10]. However, most of these collisions occur in underdeveloped nations [11,12]. ...
... ":[1,2,5,10,20,50,100,200,500] , 'n_estimators': 200, "max_leaf_nodes":[2,5,10,20,50,100], 'max_leaf_nodes': 5, ...
... ":[1,2,5,10,20,50,100,200,500] , 'n_estimators': 200, "max_leaf_nodes":[2,5,10,20,50,100], 'max_leaf_nodes': 5, ...
Road Traffic Injuries are one of the world’s leading cause of death, with greatest burden falling on nations with lower and moderate incomes. They are consistently ranked in top 10 leading causes of mortality worldwide for persons of all ages. The biggest advantage of classifying victim degree of injuries in road accidents can pave a way for safer roads and reduced accident rates. This article employs California based SWITRS dataset to propose a novel approach namely Stacked DCL-X model for classifying ``victim_degree_of_injury′′. It classifies injuries that might take place due to collisions occurring between vehicles and near by pedestrians, obstacles etc. on roads. To verify the superiority of our proposed model, several Machine Learning algorithm-based classification models are stacked together to classify ``victim_degree_of_injury′′. A total of 1 27 000 accidents are considered from SWITRS dataset when determining the ``victim_degree_of_injury′′. Machine Learning classifiers implemented in this article includes XGBoost, CatBoost, LightGBM, Decision Tree, Random Forest, Gradient Boosting and Stacked DCL-X. In addition, the algorithm used at feature selection step is Harris Hawk Optimization algorithm, a Nature Inspired Algorithm to select the best features. Prediction results shows that the proposed Stacked DCL-X model provides good stability, fewer hyper-parameters, and highest accuracy under different levels of training data volume. The values of Accuracy, Mean Square Error, and ROC-Auc in Stacked DCL-X model are 87.52, 0.5677 and 97.43, respectively. Moreover, confusion matrix and evaluation metrics of the proposed model provides better results than state-of-the-art classifiers. Statistical analysis has also been performed using Friedman’s rank test on different datasets to ensure the superiority of our proposed Stacked DCL-X model. The findings of this study would be helpful in classifying the ``victim_degree_of_injury′′. These findings are highly significant in smart city projects to effectively establish timely proactive strategies and improve road traffic safety.
... Although bus transport is safer in developed economies [1][2][3], it is replete with crashes in low and middle-income countries [4][5][6][7]. In the ensuing discussion, this study adopted a bus definition as any commercial vehicle with a capacity of at least 25 passengers [8]. ...
... Due to the low crash involvement of buses in developed countries, bus crashes have attracted few research contributions; hence the knowledge of bus crashes is comparably lower than other passenger vehicles [11]. Deplorable road infrastructure has been found to contribute to bus crashes [1]. The location of bus stops, motorists' driving attitude towards lane changing, lane width, presence of onstreet shoulder parking, posted speed limit, median width, number of lanes per direction, and number of vehicles per lane have heterogeneous effects on bus crashes. ...
... The use of intelligent speed bumps can improve the safety of buses [56]. Therefore, expanding the roadway to supply extra lanes with road medians can reduce crashes [1,5,57,58]. Also, past studies proposed surcharging drivers for errors [5] and installing CCTV surveillance at designated segments on the highway and buses [59,60]. ...
In low-and middle-income countries, approximately 70% of inter-city trips are by buses but are characterised by rampant crashes. So far, there is scarce research on the spatial characteristics of bus crashes on specific highways. This paper contributes a geospatial analysis of bus crashes along the Accra-Kumasi highway in Ghana, where 53% of crashes involved buses (2236 bus crashes in 363 crash locations along the 243 km highway). Crash locations, trends, and geospatial relationships were geolocated and analysed using descriptive statistics and heatmaps. Bus crashes occurred mainly in the catchment areas of Accra and Kumasi. Along the highway, crashes were predominant: (1) at straight road sections and curves, (2) near dense settlements, (3) around vehicle service stations such as mechanic shops and fuel filling stations, and (4) in the afternoon under clear weather conditions. The major causes of bus crashes are driver inattention, excess speeding, lane-changing, and car-following behaviour. The minor causes are driver inexperience, poor road signage, improper turning, and fatigue. Most crashes result from rear-ended and head-on collisions. Possible countermeasures include the expansion of the road lanes, installing bus surveillance technologies, specialised warning signs near crash-prone locations, and increased police monitoring and regulatory enforcement. Findings and proposed countermeasures are helpful to all low-and middle-income countries having rampant intercity and highway bus crashes.
... Bus travel is typically considered one of the safest modes of transportation, but the bus accidents remain a major concern [2]. Inexperienced and young drivers, elderly drivers, high speeds, and junction collisions all enhance the risk of injury [3]. The presence of vulnerable road users, such as pedestrians, cyclists, and motorcyclists, greatly increases the risk of serious injury or death [4]. ...
... Intersections pose particular risks, with factors like pedestrian age, vehicle type, point of impact, and weather conditions significantly impacting injury severity. Signalized intersections have higher Previously, various regression models have been used to analyze crash occurrences and the severity of road user injuries [3]. Recently, data mining techniques, both parametric and non-parametric, have become prominent for analyzing large traffic crash datasets and uncovering hidden patterns [14]. ...
This study explores the severity of bus collisions with pedestrians in Dhaka, Bangladesh, a city heavily dependent on buses for daily transportation. Using police-reported crash data (2015-2022) from the Accident Research Institute (ARI) at Bangladesh University of Engineering and Technology, the study categorizes incidents into Fatal, Grievous, Simple injury, and Collision only. The dataset encompasses factors such as crash severity, causality level, built environment, road geometry, bus characteristics, driver behavior, pedestrian factors, and collision contribution. Utilizing R Studio program, Ordered Logit models reveal significant associations between various factors and bus-pedestrian crash severity in Dhaka. The study's findings offer insights for developing strategies to mitigate bus-related pedestrian injuries in the city.
... The R-value for the ANNs forecast was the highest, coming in at around 87%, indicating that it was the most accurate (Kunt et al., 2011). Kaplan and Prato (2012) conducted a study on school bus safety and found that school buses have lower accident rates and less severe accidents than other buses., ranging from 19.8 to 37.8% (Kaplan & Prato, 2012). The reasons for this could be due to reduced driving speeds and stricter federal school bus regulations. ...
... The R-value for the ANNs forecast was the highest, coming in at around 87%, indicating that it was the most accurate (Kunt et al., 2011). Kaplan and Prato (2012) conducted a study on school bus safety and found that school buses have lower accident rates and less severe accidents than other buses., ranging from 19.8 to 37.8% (Kaplan & Prato, 2012). The reasons for this could be due to reduced driving speeds and stricter federal school bus regulations. ...
Ensuring public safety on our roads is a top priority, and the prevalence of road accidents is a major concern. Fortunately, advances in machine learning allow us to use data to predict and prevent such incidents. Our study delves into the development and implementation of machine learning techniques for predicting road accidents, using rich datasets from Catalonia and Toronto Fatal Collision. Our comprehensive research reveals that ensemble learning methods outperform other models in most prediction tasks, while Decision Tree and K-NN exhibit poor performance. Additionally, our findings highlight the complexity involved in predicting various aspects of crashes, as the Stacking Regressor shows variability in its performance across different target variables. Overall, our study provides valuable insights that can significantly contribute to ongoing efforts to reduce accidents and their consequences by enabling more accurate predictions.
... The R-value for the ANNs forecast was the highest, coming in at around 87%, indicating that it was the most accurate (Kunt et al., 2011). Kaplan and Prato (2012) conducted a study on school bus safety and found that school buses have lower accident rates and less severe accidents than other buses., ranging from 19.8 to 37.8% (Kaplan & Prato, 2012). The reasons for this could be due to reduced driving speeds and stricter federal school bus regulations. ...
... The R-value for the ANNs forecast was the highest, coming in at around 87%, indicating that it was the most accurate (Kunt et al., 2011). Kaplan and Prato (2012) conducted a study on school bus safety and found that school buses have lower accident rates and less severe accidents than other buses., ranging from 19.8 to 37.8% (Kaplan & Prato, 2012). The reasons for this could be due to reduced driving speeds and stricter federal school bus regulations. ...
Ensuring public safety on our roads is a top priority, and the prevalence of road accidents is a major concern. Fortunately, advances in machine learning allow us to use data to predict and prevent such incidents. Our study delves into the development and implementation of machine learning techniques for predicting road accidents, using rich datasets from Catalonia and Toronto Fatal Collision. Our comprehensive research reveals that ensemble learning methods outperform other models in most prediction tasks, while Decision Tree and K-NN exhibit poor performance. Additionally, our findings highlight the complexity involved in predicting various aspects of crashes, as the Stacking Regressor shows variability in its performance across different target variables. Overall, our study provides valuable insights that can significantly contribute to ongoing efforts to reduce accidents and their consequences by enabling more accurate predictions.
... Misleading interpretations of the relationship between the explanatory variables and response outcomes could arise if ordered logit is fitted in the presence of violation of the proportional odds assumption (Kaplan & Prato, 2012;Williams, 2016). Brant test is a Wald test and is commonly used for testing the parallel regression assumption (Long & Freese, 2014). ...
... The null hypothesis is that all estimated coefficients in an ordered logit model satisfy the parallel odds assumption. Hence, rejecting the null hypothesis shows that the ordered logit model is mis-specified and cannot be used to fit the data (Kaplan & Prato, 2012). ...
Poverty among widows has received little empirical attention in Africa despite women's severe vulnerability to death shock. We provided empirical evidence on widow households' transition in and out of poverty and factors influencing their probability of being in poverty. The Markov transition probabilities show moderate but increasing positive transitions for severely poor widows. Non‐poor widows are stayers who primarily sustain their non‐poor class. The ordered logit estimation shows that higher dependency ratio increases the chances of a widow being severely poor. Being an older widow and having literacy skills reduced the probability that a widow household will be severely poor. Household size and dependency ratio are noted to play important roles in the probability of transitions across poverty classes as shown by the estimated multinomial logit model. These findings are robust to alternative poverty measure, estimation method and different set of weights. Generally, the results echo the need for social safety nets to cushion widows' financial strains. Life insurance policy for spouses, increased sensitization of widows of their rights and adult education programmes targeted at widows could mitigate the negative impact of widowhood on women.
... Nghiên cứu về các yếu tố ảnh hưởng tới tai nạn và hành vi điều khiển phương tiện thiếu an toàn đối với lái xe buýt hầu hết được thực hiện tại nước phát triển. Các nghiên cứu tiêu biểu bao gồm nghiên cứu tại Florida (Mỹ) phân tích dữ liệu 4.528 vụ tai nạn liên quan tới xe buýt được ghi nhận trong giai đoạn 2003-2007 [16], nghiên cứu trên toàn Mỹ phân tích dữ liệu của 2.576 vụ tai nạn liên quan tới xe buýt [19], nghiên cứu phân tích 3.434 tai nạn liên quan tới xe buýt ở Đan Mạch xảy ra từ 2002 đến 2011 [20], nghiên cứu về 27.731 vụ tại nạn của xe buýt tại Hàn Quốc từ 2010 đến 2014 [21], nghiên cứu về 2.997 vụ tai nạn liên quan tới xe buýt nhanh tại Hàn Quốc từ 2010 đến 2016. Các nghiên cứu tại các nước đang phát triển được thực hiện ít hơn đáng kể do vấn đề dữ liệu hạn chế. ...
... Các nghiên cứu về tai nạn xe buýt nêu trên có xu hướng đi tìm hàng loạt các yếu tố ảnh hưởng. Ví dụ nghiên cứu tại Mỹ sử dụng dữ liệu từ 2005-2009 nhận ra rằng mức độ nghiêm trọng của tai nạn xe buýt gia tăng đối với lái xe rất trẻ (dưới 25 tuổi) hoặc cao tuổi (trên 55 tuổi), lái xe là nữ, trên các tuyến đường có tốc độ giới hạn rất cao (trên 65 dặm/giờ), tại các giao cắt [19]. Các nghiên cứu này đều nhất trí rằng vai trò của người điều khiển phương tiện có ý nghĩa quyết định tới việc đảm bảo (hay không đảm bảo) an toàn của dịch vụ buýt [3]. ...
Phát triển vận tải hành khách công cộng (VTHKCC) ngày càng nhận được nhiều sự quan tâm đầu tư và phát triển của chính quyền thủ đô Hà Nội. Tuy nhiên, một trong các vấn đề hiện nay là dịch vụ buýt đang đánh mất đi cảm tình và sự yêu quý của người dân do các hành vi lái xe nguy hiểm của lái xe buýt. Với mục tiêu tìm hiểu nguyên nhân của việc vượt đèn vàng của lái xe buýt, chúng tôi thực hiện nghiên cứu này trên cơ sở dữ liệu từ 320 lái xe buýt đang làm việc cho Tổng công ty vận tải Hà Nội (Transerco). Kết quả nghiên cứu của chúng tôi chỉ ra rằng áp lực công việc từ thời gian biểu, tình trạng tắc đường và trên cabin xe là những yếu tố chính thúc đẩy hành vi này. Bên cạnh đó, các lái xe giàu kinh nghiệm và từng có hành vi vi phạm quy định của công ty sẽ có xu hướng thực hiện hành vi lái xe vượt đèn vàng nhiều hơn. Trên cơ sở kết quả các yếu tố ảnh hưởng, một số giải pháp đã được đề xuất để hạn chế tình trạng này
... Chenzhu recently reviewed a significant body of literature on rear-end accident analysis methods that use real accident data to evaluate the contribution of critical factors to injury severity in a crash. Currently, the most common methods for analyzing risk factors in crashes are categorized into 2 main groups based on logit and probit models, which include the ordered logit/probit model (Kockelman and Kweon 2002;Kim et al. 2007;Kaplan and Prato 2012), bivariate generalized ordered probit model (Yamamoto and Shankar 2004;Yuan et al. 2020;Zhang et al. 2022;Zhou et al. 2022), and random parameters ordered logit/probit model (Anastasopoulos et al. 2012;Sadri et al. 2013;Anarkooli et al. 2017;Sun et al. 2022;Okafor et al. 2023;Se et al. 2023;Zeng et al. 2023). ...
... Mohammed A. Quddus (2002) employed ordered probit models to examine the levels of motorcycle injury severity and vehicle damage severity. Kaplan and Prato (2012) utilized a generalized ordered logit model to estimate the risk factors that contribute to bus accident severity in the United States, from driver physiological characteristics to speed limits. Chiou (2013) used a bivariate generalized ordered probit model to identify several risk factors associated with the severity of 2-vehicle crashes. ...
Objective:
Angle crashes have been acknowledged as a concerning issue in the traffic safety field, though there is limited understanding of the contributions of risk factors to injury severity. This article aims to examine the impact of risk factors and unobserved heterogeneity on the severity of driver injuries in angle collisions by utilizing angle crash data in the United States from 2016 to 2021.
Methods:
The relationship between risk factors and driver injury severities in angle crashes was investigated using a random parameter bivariate ordered probit model (RPBOP) with 4 categories of injury severity classified as outcome variables, including no injury, possible injury, minor injury, and serious jury. Risk factors were considered as explanatory variables, classified as driver characteristics, vehicle characteristics, road characteristics, environmental characteristics, time characteristics, and crash characteristics. Bayesian inference was used to assess the unobserved heterogeneity in risk factors, and marginal effects were computed to analyze the effect of each factor on injury outcomes.
Results:
The findings demonstrate that risk factors have varying effects on driver involvement in angle crashes. Certain factors exhibited unobserved heterogeneity, including young drivers (ages 25-44), older drivers (over age 59), road grade, and collision point orientation. On the other hand, other factors, such as female gender, motorcycles, intersections, speed limit (>50 mph), poor lighting conditions, adverse weather, urban areas, and workdays, were shown to significantly increase the likelihood of driver injury in angle collisions, as well as increase susceptibility to fatal injury.
Conclusions:
This article offers new insights into reducing driver injuries in angle crashes and has the potential to inform policy development aimed at preventing such incidents. Further research could utilize multisource data fusion and investigate the spatiotemporal stability of risk factors to enhance the generalizability of angle collision prevention strategies.
... Typically, a speeding-related crash is determined if any driver involved is charged with a speeding-related offense or if the police officer indicates that the car was racing, driving too fast for the conditions, or exceeding the posted speed limit. A number of studies use "speeding driving" as an explanatory variable in the model (Lemp et al. 2011;Kaplan and Prato 2012;Osman et al. 2018;Rezapour et al. 2019;Zhang and Hassan 2019;Se et al. 2021b). Various studies have identified the effects of specific factors (e.g., age, education, sleep quality, area, impaired driving, vehicle type, and lighting con-dition) on speeding behaviors (Shyhalla 2014;Chevalier et al. 2016;Tseng et al. 2016;Yadav and Velaga 2020). ...
... It is impossible to take all factors into consideration when modeling crash severity, which may result in unobserved heterogeneity (Behnood and Mannering 2019;. The random-parameter ordered model framework was developed to capture the unobserved heterogeneity, such as the random parameter ordered logit model, random parameter ordered probit model, and generalized ordered logit model (Kaplan and Prato 2012;Jalayer et al. 2018;Osman et al. 2018;Zhang and Hassan 2019;Azimi et al. 2020). Furthermore, the random-parameter ordered model framework was extended by considering the potential correlation between parameters and heterogeneity in the means of random parameters Fountas et al. 2021;Se et al. 2021b). ...
This study investigates the differences in the factors affecting the injury severity of speeding-related crashes occurring in the daytime and nighttime. Two log-likelihood ratio tests are conducted to validate whether speeding-related crashes classified by daytime and nighttime should be modeled separately. The result proves that separate modeling is necessary. Two correlated random parameter order probit models with heterogeneity in means are conducted using the data collected from 2018 to 2020 in the United States. Model estimation results show that urban areas, speed limits, and young and older drivers are temporal instability. Angle crashes, head-on crashes, intersections, downhill, exceeding the speed limit, drunk driving, and motorcycles are statistically significant in both models with an increased crash severity. Interaction and heterogeneity effects between random parameters are also reported. For instance, large trucks driving above the speed limit are more likely to increase the probability of severe injury.
... Logit, multinomial logit, and ordered logit models in their standard or modified formats have been extensively used for forecasting accident injuries, accident severity analysis, and crash type predictions (Yasmin et al., 2014;Fiskin et al., 2021;Azimi et al., 2020;Anarkooli et al., 2017;Hosseinzadeh et al., 2021;Kaplan and Prato, 2012;Wu et al., 2020;Chen et al., 2020a;Wang et al., 2021). Although the use of an ordered logit model and multinomial logit model for a hazardous cargo ship berthing accident severity analysis is a new approach, their use for an accident severity analysis considering the unobserved heterogeneity at play is well acknowledged in the literature. ...
... It is suitable for use when the response variable has three or more ordered categories with a natural ordering but does not possess equal intervals. The relationship between the independent variables and the probability of the response falling into each category is modeled using cumulative logits (log-odds) (Kaplan and Prato, 2012). The model assumes that the log-odds of the response variable falling into a particular category versus falling into any of the lower categories follow a linear relationship with the independent variables. ...
Ship berthing is an intricate operation with a high accident rate, the consequence severity of which is further augmented by the presence of hazardous cargo. An understanding of the role of various accident causation factors will improve hazardous cargo ship berthing safety through the establishment of pragmatic and efficient countermeasures. Therefore, this study investigated 348 hazardous cargo ship berthing accidents between 1960 and 2018. An ordered logit regression model was used to determine the systematic unobserved heterogeneity among the accident data and account for parameter calibration. The impact of each causation factor was analyzed by exploring model parameter estimates, the odds ratio (OR), and pseudo-elasticity. The results revealed that several human factor traits, such as experience, pilot, and errors and violations alongside the weather, visibility, number of tugboats, and the port safety and emergency mechanism had a significant impact on the consequence severity of hazardous cargo ship berthing accidents. Based on these insights, this study proposed a pragmatic approach to reduce the hazardous cargo ship berthing risk and diminish the consequence severity.
... As part of our quantitative analysis we explored the standard ordered response model in the form of the ordered logistic regression model and its generalizations including the partial proportional odds model to analyse our data [24,25]. The ordered logistic regression model is an econometric technique used when the dependent variable is measured in ordinal scale [26]. ...
... where β 1 is a vector of parameters that does not violate parael-lines assumption and is associated to a subset X 1i of the independent variables, and β 2j is a vector of parameters that vary according to the cut point of the ordered logit model and is associated to a subset X 2i of the independent variables [24,25]. ...
Short-term land rental agreements such as the traditional conacre system in Northern Ireland offer flexibility between the landowners and the farmers renting the land. However, the uncertainty of tenure linked to such short-term land rental systems does not allow for farmers renting the land to make longer-term investment planning and decisions, particularly around sustainable land management practices. Long-term tenancy agreements have been identified as a viable option to cope with short-term uncertainties and improve the environmental management of the land. In this study, we analysed the factors influencing farmers’ intention to adopt long-term land leasing with and without income tax incentives in Northern Ireland. To achieve our objective, we employed ordered logistic regression models complemented with qualitative analysis. The results of our analyses showed that varying factors including risk attitude, pro-environmental behaviour, profit consciousness, having a dairy enterprise, the area of farmland owned, the presence of a successor, and the age and education of the farmer influence farmers’ intention to adopt long-term land leasing. However, variability exists depending on the farmers’ rental status and availability of income tax incentives. It can be concluded from the study that policies aimed at encouraging long-term land leasing should take a holistic approach that incorporates environmental and socioeconomic factors.
... MSE is the weighted mean of the sum of squares of the distances that predicted value deviates from the real value. The five performance metrics are shown in Formulas (7)(8)(9)(10). It can be seen from the Figure 8 that the four heuristic algorithms except PRE have improved better than the original SVM, and all indicators are not lower than 80%. ...
... sum of squares of the distances that predicted value deviates from the real value. The five performance metrics are shown in Formulas (7)(8)(9)(10). It can be seen from the Figure 8 that the four heuristic algorithms except PRE have improved better than the original SVM, and all indicators are not lower than 80%. ...
Traffic accidents on urban roads are a major cause of death despite the development of traffic safety measures. However, the prediction of casualties in urban road traffic accidents has not been deeply explored in previous research. Effective forecasting methods for the casualties of traffic accidents can improve the manner of traffic accident warnings, further avoiding unnecessary loss. This paper provides a practicable model for traffic forecast problems, in which ten variables, including time characteristics, weather factors, accident types, collision characteristics, and road environment conditions, were selected as independent factors. A mixed-support vector machine (SVM) with a genetic algorithm (GA), sparrow search algorithm (SSA), grey wolf optimizer algorithm (GWO) and particle swarm optimization algorithm (PSO) separately are proposed to predict the casualties of collisions. Grounded on 4285 valid urban road traffic collisions, the computing results show that the SSA-SVM performs effectively in the casualties forecast compared with the GWO-SVM, GA-SVM and PSO-SVM.
... La metodología a emplear incluye el levantamiento y tratamiento de los datos proporcionados por la Superintendencia de Transporte Terrestre de Personas, Carga y Mercadería (SUTRAN) y la Policía Nacional del Perú (PNP), una prueba de hipótesis, el análisis de los resultados y finalmente la presentación de conclusiones del estudio.II. ESTADO DEL ARTEEn muchos países desarrollados, los autobuses se consideran un modo relativamente seguro de transporte[1] aunque el número de accidentes esté lejos de ser despreciable[2]. Por este motivo, a pesar que no existen muchos estudios al respecto, los últimos años hay un interés creciente en la mejora de la seguridad de las operaciones de autobuses en todo el mundo.Existen muchos estudios que identifican los factores causantes de los accidentes, entre los cuales se pueden identificar las características del conductor y el comportamiento del conductor, las características de infraestructura, condiciones ambientales, tipo de colisión y la interacción con otros usuarios de la carretera[2]. ...
... ESTADO DEL ARTEEn muchos países desarrollados, los autobuses se consideran un modo relativamente seguro de transporte[1] aunque el número de accidentes esté lejos de ser despreciable[2]. Por este motivo, a pesar que no existen muchos estudios al respecto, los últimos años hay un interés creciente en la mejora de la seguridad de las operaciones de autobuses en todo el mundo.Existen muchos estudios que identifican los factores causantes de los accidentes, entre los cuales se pueden identificar las características del conductor y el comportamiento del conductor, las características de infraestructura, condiciones ambientales, tipo de colisión y la interacción con otros usuarios de la carretera[2]. Dependiendo del país se puede incluir la antigüedad de los autobuses como factor causante, pero las leyes cada vez son más estrictas y ponen límites de antigüedad más exigentes, con lo que ya no se debe considera como factor importante. LaFig. 1muestra la comparación de la antigüedad permitida en el Perú con algunos países de la región de acuerdo con el Informe 019-2008-MTC/15.0 ...
... Transport vehicles that pass through these sharp curves and bends often lack the navigation to pass safely through these curves, leading to collision, rolling over of vehicles, and plunging off the cliff (See Figure 1 below). Such accidents not only result in severe casualties but also lead to road closures for extended periods, requiring the deployment of heavy machinery for vehicle recovery and repairs [2]. The disruption caused extends beyond immediate safety concerns, impacting transportation networks and incurring high financial and logistical costs. ...
... Binary Logit Model (Sze and Wong, 2007, Pervez et al., 2022 Multinomial Logit Model (Tay et al., 2011, Chen and Fan, 2019b, Qiu and Fan, 2022) Ordered Logit/Probit Models (Rifaat andChin, 2007, Kaplan andPrato, 2012) Partial proportion odds Model (Wang and Abdel-Aty, 2008, Song and Fan, 2020, Li and Fan, 2020) Mixed/ Random Parameter Logit Model (Qiu and Fan, 2022, Chen and Fan, 2019a, Kim et al., 2010, Rella Riccardi et al., 2023 Random Parameter Logit Model with Heterogeneity in Means and Variance , Behnood and Mannering, 2017a, Behnood and Mannering, 2017b, Adanu et al., 2022, Barbour et al., 2024, Dzinyela et al., 2024, Alnawmasi and Mannering, 2019, Hossain et al., 2024 captured year-to-year temporal trends and their associated factors, translating these insights into actionable policy measures remains challenging. ...
Pedestrians are the most at-risk group in the transportation system, experiencing a troubling and persistent rise in both the frequency and proportion of fatalities over the past decade. In 2022, pedestrian fatalities in the United States reached a record high since1981. Despite extensive research examining crash severity models from various perspectives, there is a notable paucity of studies investigating the impact of seasonal variations.
This study addresses this gap by examining the seasonal variation in potential contributing
factors to pedestrian-vehicle crash severity, utilizing nine years of the most recent pedestrian crash data from North Carolina. Preliminary analysis shows higher crash frequencies
during darker seasons, with the highest frequency observed in the fall. Seasonally temporally constrained random parameter logit models, incorporating heterogeneity in both means and variances, are employed to explain the unobserved heterogeneity inherent in the variables and to mitigate biased parameter estimation. The necessity for segmentation is corroborated through pairs of likelihood ratio tests. The model outcomes reveal significant seasonal variations in several important variables. For instance, hit-and-run incidents exhibit the highest marginal effects in the spring. During the summer, male drivers, weekends, and alcohol impairment for both drivers and pedestrians have the most substantial marginal effects. In the fall, young drivers (aged under 24), darkness irrespective of lighting, and work zones show the highest magnitude of marginal effects. This study offers a
novel perspective on pedestrian safety analysis and provides data-driven recommendations to enhance safety planning, resource allocation, and overall improvements in the
transportation system.
... This study contradicts 22 (Sam et al., 2018) (5) claim that the absence of a median raises the severity of bus/minibus acci-23 dents by 29.5%. Although the influence of road medians on traffic safety has been inconsistent, 24 the majority of research (Barua & Tay, 2010;Kaplan & Prato, 2012) (2, 24) have found positive 25 effects. These studies show that road medians are related with decreased accident severity (Barua 26 & Tay, 2010) (2) and reduced fatalities (Kaplan & Prato, 2012) (24). ...
This study explores the severity of bus/minibus collisions in Dhaka, Bangladesh, a city heavily dependent on buses for daily transportation. Using police-reported crash data (2015-2022) from the Accident Research Institute (ARI) at Bangladesh University of Engineering and Technology. The study categorizes injury severity into fatal, major injury, minor injury, and property damage only. The dataset includes a range of factors, such as crash severity, year, gender, age, drunk driving, day of the week, time of day, light conditions, weather conditions, manner of collision, number of vehicles involved, traffic control, location, road geometry, road separation/dividers, road surface type, road surface condition, and traffic flow. An Ordered Logit model was developed using R Studio to identify significant associations between these factors and crash severity. The model reveals how variables such as gender, age, time of day, collision features, and road conditions contribute to the severity of crashes in Dhaka. The study's findings offer insights for developing strategies to mitigate bus/minibus-related crash injuries in the Dhaka City.
... Buses, as an integral part of public transit, are essential for ensuring the safe operation of public transportation and maintaining the efficiency of urban passenger transport systems. Public buses are generally considered safer than other modes of transportation [1,2]. However, due to the complexity of urban road traffic environments, it is difficult to avoid public transportation accidents. ...
Currently, there is a lack of a comprehensive and integrated method for assessing risk levels of bus drivers. This study utilizes XGBOOST and Logistic regression models to analyze the impact of various indicator features of bus drivers on crash risks. A grey whitening weight function model is then constructed to evaluate the risk levels of bus drivers, achieving a quantified assessment of their risk levels. Based on the research findings, the following observations were made: (1) The number of non-fault crashes is the most important risk feature influencing the occurrence of at-fault crashes. (2) Features related to crashes, violations, and alarms, as well as age, bus driving experience, driving experience, route length, and the number of stops, have a negative impact on the occurrence of at-fault crashes. (3) The study quantifies bus drivers into five risk levels, with higher levels indicating higher risk. It was found that 94.94% of bus drivers are in the second and third risk levels, 4.93% in the first and fourth risk levels, and only 0.12% of bus drivers are in the highest fifth risk level. The conclusions drawn in this study, along with the proposed method for evaluating risk levels of bus drivers, will contribute to the evaluation and management of bus drivers by bus companies and transportation authorities, thereby reducing crashes in public transportation.
... Điều này có thể được giải thích là do những lái xe mới họ thường có ý thức tốt hơn và tôn trọng quy định của doanh nghiệp buýt nhiều hơn. Một số nghiên cứu về an toàn trước đây cũng chỉ ra rằng những lao động mới có xu hướng tuân thủ các quy định về an toàn tốt hơn những người lâu năm [23,24]. ...
Phát triển vận tải hành khách công cộng là ưu tiên hàng đầu của chính quyền các đô thị trong xây dựng một thành phố phát triển văn minh và xanh. Tuy nhiên, để khuyến khích người dân sử dụng dịch vụ này là điều không dễ dàng vì chất lượng dịch vụ còn nhiều hạn chế. Một trong các vấn đề khiến hành khách chưa hài lòng với dịch vụ buýt là thái độ của lái xe đối với hành khách chưa thực sự tốt dẫn đến chất lượng dịch vụ bị đánh giá kém và ngày càng ít người sử dụng dịch vụ buýt. Trong nghiên cứu này, chúng tôi tập trung phân tích tác động của áp lực công việc đến việc lái xe có các hành vi tiêu cực, mất lịch sự đối với hành khách. Dữ liệu được thu thập từ 428 lái xe trên mạng lưới buýt Hà Nội. Phương pháp phân tích nhân tố khám phá được áp dụng để nhận diện 04 nhóm yếu tố áp lực gồm : (1) Áp lực cabin và phương tiện, (2) Áp lực thời gian làm việc, (3) Áp lực đường sá, (4) Áp lực thời tiết. Những lái xe có xu hướng thực hiện các hành vi tiêu cực đối với hành khách là những người trên 45 tuổi và có kinh nghiệm trên 2 năm. Trong 4 nhóm yếu tố áp lực, áp lực từ thời gian làm việc và áp lực từ đường sá là các yếu tố mạnh nhất thúc đẩy người người lái xe thực hiện các hành vi tiêu cực đối với hành khách. Trên cơ sở các yếu tố ảnh hưởng, một số giải pháp để hạn chế tác động tiêu cực của các yếu tố được đề xuất
... Analyzing the causes of accidents in detail, Kaplan and Prato (2012) state that bus accident risk factors include driver characteristics and driver behavior, infrastructure characteristics, environmental conditions, type of collision and interaction with other road users. They do not consider the age of the bus since no significant relationship was found with the severity of the accident, possibly related to the short age of the bus fleet studied (6.6 years on average). ...
... xi More detail sees Chen et al. (2016), Abegaz et al. (2014), and Kaplan and Prato (2012). xii Edited from Chen et al. (2016). ...
This study aims to examine the risky motorcycle riding behaviors among young people in Thailand. An Ordered Logit Model is used to evaluate the association between motorcycle drivers (ages 15–24 years), accident characteristics, and accident outcomes (including deaths, permanent disabilities, and injuries). The study finds that the two main characteristics of youth associated with risk-taking behaviors are driving without a helmet and being under the influence of alcohol or other drugs. Young males are significantly more likely to be driving recklessly and are involved in more severe crashes than females. In an effort to prevent road traffic accidents among youth, effective training courses must be implemented, especially motorbike-riding skills for safety. These include addressing the major risk factors, through legislation and enforcement, and by educating teenagers and young adults about the use of protective equipment.
... The most popular approach is regression modeling and its derivatives. For example, ordered-logit models (Chen et al., 2015;Kaplan & Prato, 2012), ordered-probit models (Chiou et al., 2013;Wang et al., 2022), and logistic regression models (Wang et al., 2021) have been widely utilized. Similar to prior analyses, these investigations were restricted by their use of a small number of potential variables and their narrow emphasis on specific topics. ...
... The result of the model establishment represents that drivers' age (46)(47)(48)(49)(50)(51)(52)(53)(54)(55), aggressive and violent drivers, and the presence of insomnia were influencing factors at the driver level, and weather condition variables at the vehicle level affected bus accidents. Kaplan and Prato [15] used an ordered logit model to extract risk factors for the severity of British bus accidents. The analysis showed variables such as driver's age (under 25, over 65), speed limit (over 65 mph, less than 20 mph), and intersection were found to affect the severity of the bus accident. ...
As intercity buses are a mode that moves large-scale occupancy between regions, it accounts for the mode share-means for mid- to long-distance movement in South Korea. However, the study of intercity bus safety needs to be more extensive, and safety policies are carried out based on traditional probability models without considering the data characteristics of bus accidents. Therefore, in this study, the Random Parameter Ordered Logit model was applied to derive fixed parameter factors that have the same effect on the severity of intercity bus accidents and Random Parameters that consider the heterogeneity of unique attributes by accident. It also analyzed the marginal effect of intercity bus accident severity. As a result of this study, the influencing factors that reflect heterogeneity with random parameters were driver’s condition: drowsiness, vehicle size: medium, crash type: vehicle–pedestrian accident, road condition: wet pavement, and log form of AADT. The random parameter ordered logit model was traditionally found to be more suitable than the ordinal logit model, which only reflects fixed factors and more reliable predictions considering the heterogeneity of accident characteristics for each observation.
... Various factors contribute to bus safety, such as weather, time, environmental factors and bus type [6], road conditions and bus drivers' socio-demographic characteristics [7]. However, the driving behaviour of bus drivers remains the primary cause of bus accidents [8]. ...
... Another group of studies attempt to predict accidents. Regardless of the purpose of analysis, identified factors, or predictions, two important tools for investigating and analysing accidents are statistical models (e.g., Vajari et al., 2020;Kaplan and Prato, 2012;Gray et al., 2008;Eluru et al., 2008) and machine learning models. ...
Traffic accidents around the world cause significant economic, human, and social losses annually. As a result, they have always involved their own macro policies and executive plans. Proper planning in this area requires a thorough understanding of traffic accidents. Identifying and analyzing the causes of traffic accidents help make better predictions about them and the severity of their injuries. In addition to the well-cited reasons such as vehicle and road conditions, this study explored driver's decision-making style as one of the factors affecting the severity of traffic accidents. The purpose of this study was to predict traffic accidents and the severity of their injuries by considering the decision-making style of drivers. To this end, we developed and analyzed different scenarios according to a variety of data sorting modes, data pre-processing methods, and various classifiers based on machine learning. The results showed that considering the decision-making style has a positive impact on the performance of the prediction model. It was also found that the best-case scenario occurs under the following conditions: (1) all the data alongside decision-making style are presented to the model, (2) outliers are excluded in a permissive mode, and (3) the AdaBoost classifier is used for making predictions.
... The result of the model establishment represents that drivers' age (46-55), aggressive and violent drivers, and the presence of insomnia were influencing factors at the driver level, and weather condition variables at the vehicle level affected bus accidents. Kaplan and Prato [10] used an ordered logit model to extract risk factors for the severity of British bus accidents. ...
As intercity buses are a mode that moves large scaled occupancy between regions, it accounts for the mode share-means for mid to long-distance movement in South Korea. However, the study on intercity bus safety needs to be more extensive, and safety policies are carried out based on traditional probability models without considering the data characteristics of bus accidents. Therefore, in this study, the Random Parameter Ordered Logit model was applied to derive fixed parameter factors that have the same effect on the severity of intercity bus accidents and random parameters that consider the heterogeneity of unique attributes by accident. It also analyzed the marginal effect of intercity bus accident severity. As a result of the study discovered that the influencing factors that reflect heterogeneity with Random Parameters were driver’s condition: drowsiness, vehicle size: medium, crash type: vehicle-pedestrian accident, road condition: wet pavement, and log form of AADT. The random parameter ordered logit model was traditionally found to be more suitable than the ordinal logit model, which only reflects fixed factors and more reliable predictions considering the heterogeneity of accident characteristics for each observation.
... Statistical methods have been widely used to predict traffic accidents by examining patterns, trends, and underlying factors [8]. Regression models have been commonly used to analyze the risk factors associated with traffic accidents [9][10][11]. However, these models rely on pre-defined assumptions regarding the underlying probability data distribution and the dependent relationships among various variables which may not always align with the actual circumstances [12]. ...
Traffic accidents directly influence public safety and economic development; thus, the prevention of traffic accidents is of great importance in urban transportation. The accurate prediction of traffic accidents can assist traffic departments to better control and prevent accidents. Thus, this paper proposes a deep learning method named attention-based residual dilated network (ARDN), to extract essential information from multi-source datasets and enhance accident prediction accuracy. The method utilizes bidirectional long short-term memory to model sequential information and incorporates an attention mechanism to recalibrate weights. Furthermore, a dilated residual layer is adopted to capture long term information effectively. Feature encoding is also employed to incorporate natural language descriptions and point-of-interest data. Experimental evaluations of datasets collected from Austin and Houston demonstrate that ARDN outperforms a range of machine learning methods, such as logistic regression, gradient boosting, Xgboost, and deep learning methods. The ablation experiments further confirm the indispensability of each component in the proposed method.
... When the injury severity changes from 1 to 2, it depends on µ 2 X 2 . The probabilistic model of the ordered logit can be expressed as follows [44]: ...
Many studies have analyzed the road characteristics that affect the severity of truck crashes. However, most of these studies have only examined road alignment or grade separately, without considering their combined effects. The purpose of this article is to address this gap in the literature. Our study uses truck crash data from 2015 to 2019 on freeways in the Yunnan Province of China, where the severity levels of the crashes were determined by taking into account economic loss and the number of injuries and fatalities. Our study develops three models to examine the severity of truck crashes: a multinomial logit model, a mixed logit model, and a generalized ordered logit model. The findings suggest that the mixed logit model, which can suffer from unobserved heterogeneity, is more suitable because of the higher pseudo-R-squared (ρ²) value and lower Akaike Information Criterion and Bayesian Information Criterion. The estimation results show that the combination of curve and slope significantly increases the severity of truck crashes compared to curves and slopes alone. In addition, risk factors such as crash type, vehicle type, surface condition, time of day, pavement structure, and guardrails have a significant impact on the severity of truck crashes on mountainous freeways. Based on these findings, we developed policy recommendations for reducing the severity of multi-truck collisions on mountainous highways and improving transport sustainability. For example, if possible, the combination of curve and slope should be avoided. Additionally, it is recommended that trucks use tires with good heat resistance.
... Regarding bus crash severity, drivers' profiles are most frequently studied. For instance, Kaplan and Prato (2012) found that bus crash severity increased with the presence of bus drivers under the age of 25 or older than 65. Other studies found that female, fatigued, and inexperienced bus drivers (Evans & Courtney, 1985;Huting et al., 2016;Samerei et al., 2021a) and those with a history of traffic violations are more likely to be involved in bus crash (Feng et al., 2016). ...
In road safety research, bus crashes are particularly noteworthy because of the large number of bus passengers involved and the challenge that it puts to the road network (with the closure of multiple lanes or entire roads for hours) and the public health care system (with multiple injuries that need to be dispatched to public hospitals within a short time). The significance of improving bus safety is high in cities heavily relying on buses as a major means of public transport. The recent paradigm shifts of road design from primarily vehicle-oriented to people-oriented urge us to examine street and pedestrian behavioural factors more closely. Notably, the street environment is highly dynamic, corresponding to different times of the day. To fill this research gap, this study leverages a rich dataset - video data from bus dashcam footage - to identify some high-risk factors for estimating the frequency of bus crashes. This research applies deep learning models and computer vision techniques and constructs a series of behavioural and street factors: pedestrian exposure factors, pedestrian jaywalking, bus stop crowding, sidewalk railing, and sharp turning locations. Important risk factors are identified, and future planning interventions are suggested. In particular, road safety administrations need to devote more efforts to improve bus safety along streets with a high volume of pedestrians, recognise the importance of protection railing in protecting pedestrians during serious bus crashes, and take measures to ease bus stop crowding to prevent slight bus injuries.
... Mansour Hadji Hosseinlou utilized a zero-truncated Poisson model to confirm that speeding violations and collisions were positively correlated [19]. Sigal Kaplan utilized an ordered generalized logit model [20]. It was discovered that the accident rate was raised when a vehicle exceeded or fell below the minimum speed requirement for road travel. ...
The number and severity of bus traffic accidents are increasing annually. Therefore, this paper uses the historical data of Chongqing Liangjiang Public Transportation Co., Ltd. bus driver safety violations, service violations, and road traffic accidents from January to June 2022 and constructs road traffic accident prediction models using Extra Trees, BP Neural Network, Support Vector Machine, Gradient Boosting Tree, and XGBoost. The effects of safety and service violations on vehicular accidents are investigated. The quality of the prediction models is measured by five indicators: goodness of fit, mean square error, root mean square error, mean absolute error, and mean absolute percentage error. The results indicate that the XGBoost model provides the most accurate predictions. Additionally, simultaneously considering safety and service violations can improve the accuracy of the model’s predictions compared to a model that only considers safety violations. Bus safety violations, bus service violations, and bus safety operation violations significantly influence traffic accidents, which account for 27.9%, 20%, and 16.5%, respectively. In addition to safety violations, the service violation systems established by bus companies, such as bus service codes, can be an effective method of regulating the behavior of bus drivers and reducing accidents. They are improving both the safety and quality of public transportation.
... Para este caso, que se puede saber luego de aplicar el test de Wald (Williams, 2006), puede obtenerse un modelo ajustado a tal situación, que muestre los coeficientes de las variables que no han violado el supuesto de líneas paralelas, junto con aquéllas que si lo hicieron. En este caso, se obtendría un modelo que viola, de manera parcial, dicho supuesto (Kaplan & Prato, 2012): ...
El propósito de este artículo consiste en analizar los factores de riesgo asociados con el oficio de mototaxista en la ciudad de Cartagena de Indias (Colombia) para determinar su influencia en las percepciones de traumatismos causados por el tránsito; en especial, las percepciones de accidentalidad y de lesiones. Para ello, se aplicó un cuestionario estructurado, mediante la técnica de encuesta, a una muestra representativa de 403 personas que ejercen el oficio de mototaxista en la ciudad, asumiendo una población infinita y tomando como referencia un nivel de confianza del 95 % y un error muestral del 4,9 %. Para ello, se utilizó el modelo Logit ordenado para determinar la relación entre los factores de riesgo y las percepciones de los mototaxistas, en función de dos modelos: percepción de accidentalidad y percepción de lesiones de tránsito. Los resultados evidenciaron que las variables con mayor influencia para ambos modelos fueron la exposición al viento, por afectaciones en cuanto al manejo y velocidad que presentan las ráfagas de viento; la inseguridad, asociada con las condiciones de las vías, en materia de señalización, estado del pavimento, entre otras; y la ergonomía, referida a la exposición a malas posturas durante el ejercicio del oficio.
... Many studies have evaluated and analyzed crash risks in relation to bus accidents [2,[5][6][7][8][9][10][11][12][13][14][15][16][17][18]. However, most studies have focused on collision accidents. ...
Owing to the low occurrence of public transport accidents, most existing studies have focused on improving the traffic safety of passenger cars. However, traffic accidents related to public transport should also be investigated for the safety of public transport users, particularly the vulnerable ones. This study analyzed the behavioral factors affecting passenger fall incidents on buses to enhance the safety of public bus passengers. This study considered potential influential factors, such as acceleration, deceleration, braking, and steering maneuvers, calculated using data from digital tachographs installed on the buses. Negative binomial and Poisson lognormal regression models were built using the Bayesian method. The two models yielded similar results. In all cases, deceleration-related behavioral factors (abrupt deceleration and abrupt stop) significantly influenced passenger fall incidents. The findings from this study are significant for establishing effective strategies to reduce fall incidents by providing safety education to bus drivers.
... However, accident reports or videos might ignore some essential details, which means some remedies might be necessary [86]. Many countries have invested a lot in accident data collection, resulting in many famous accident databases, such as CIDAS [87] and NAIS [88] from China, GIDAS [89] from German, GES [90] from the US, ASSESS [91] from Europe, OTS [92] and STATS19 [92] from the UK. Several accident datasets are analyzed in [93]. ...
Automated driving is a promising tool for reducing traffic accidents. While some companies claim that many cutting-edge automated driving functions have been developed, how to evaluate the safety of automated vehicles remains an open question, which has become a crucial bottleneck. Scenario-based testing has been introduced to test automated vehicles, and much progress has been achieved. While data-driven and knowledge-based approaches are hot research topics, this survey is mainly about Data-Driven Scenario Generation (DDSG) for automated vehicle testing. Rather than describe the contributions of every study respectively, in this survey, methodologies from various studies are anatomized as solutions for several significant problems and compared with each other. This way, scholars and engineers can quickly find state-of-the-art approaches to the issues they might encounter. Furthermore, several critical challenges that might hinder DDSG are described, and responding solutions are presented at the end of this survey.
Understanding the adoption of electric vehicles (EVs) in the used vehicle market is crucial for achieving mass market penetration. This area, however, remains relatively under-studied. This research aims to understand the new-versus-used vehicle choice behavior and the consequent vehicle ownership cost by analyzing consumer expenditure survey data that tracks households’ expenditure on vehicle acquisition and operation on a national scale (U.S.). The motivation is to understand how much households who generally purchase used vehicles can gain or lose if they transition to a used EV instead. The choice model and cluster analysis conducted show that ownership of used vehicles is associated with family size, income, housing tenure, and age. Additionally, for lower-income renters, vehicle ownership and purchase costs tend to consume a high fraction of their household income, raising equity concerns and indicating that these households need particular consideration while encouraging the EV transition. Moreover, while the current average price paid for a used conventional vehicle is approximately 9,177 to $37,078 depending on the electric range and whether it is a luxury or an economy segment vehicle. This price disparity suggests the need for incentives to encourage the used EV market. The current study can serve as a starting point and can be of interest to stakeholders, such as policymakers, who can be informed about what is necessary for potential buyers of used EVs to transition to EVs.
Public buses and taxis play crucial roles in urban transportation. Ensuring their safety is of paramount importance to develop sustainable communities. This study investigated the significant factors contributing to the injury severity of bus–taxi crashes, using the crash data recorded by the police in Hong Kong from 2009 to 2019. To account for the unobserved heterogeneity, the random parameters logistic model with heterogeneity in means was elaborately developed. The results revealed that taxi driver age, bus age, traffic congestion, and taxi driver behavior had significantly heterogeneous effects on the injury severity of bus-taxi crashes and that the mean value of the random parameter for severe traffic congestion was likely to increase if the taxi’s age was less than five years. Taxi driver gender, rainfall, time of day, crash location, bus driver behavior, and collision type were found to significantly affect the bus–taxi crash severity. Specifically, female taxi drivers, old taxis, rainfall, midnight, improper manipulation of bus and taxi drivers, head-on and sideswipe collision types, and non-intersections were associated with a higher likelihood of fatal and severe crashes. Based on our findings, targeted countermeasures were proposed to mitigate the injury severity of bus–taxi crashes.
div class="section abstract"> The head injury mechanisms of occupants in traffic accidents will be more complicated due to the diversified seating postures in autonomous driving environments. The injury risks and assessment parameters in complex collision conditions need to be investigated thoroughly. Mining the simulation data by the support vector machine (SVM) and the random forest algorithms, some head injury predictive models for a 6-year-old child occupant under a frontal 100% overlap rigid barrier crash scenario were developed. In these head injury predictive models, the impact speed and sitting posture of the occupant were considered as the input variables. All of these head injury predictive models were validated to have good regression and reliability (R2>0.93) by the ten-fold cross-validation. When the collision speed is less than 60km/h, rotational load is the primary factor leading to head injury, and the trends of BrIC, von Mise stress, Maxshear stress, and MPS are similar. However, when the speed exceeds 60km/h, brain injuries are primarily affected by linear load. The head 3ms acceleration, HIC15, von Mise stress, Maxshear, and MPS have a consistent trend. The causes of head injury are mainly affected by the collision speed and sitting angle. Therefore, in autonomous driving scenarios, the design of child restraint systems should fully consider the influence of collision speed and sitting posture on the risk and mechanism of injury, improving the phenomenon of occupant submarine and head restraint insufficiency under the large angle sitting posture. This research will establish a theoretical foundation for investigating head injury mechanisms, injury thresholds, and the consistency of injury indices, and will provide data support for enhancing the restraint system and virtual testing.
</div
A suitable mechanism for evaluating the safety of the highway bus industry is crucial for ensuring public transportation safety in a country. In this study, we have combined indices from the Compliance Safety Accountability (CSA) program of the Federal Motor Carrier Safety Administration (FMCSA) in the US, the safety evaluation of renting buses in Japan, and some existing safety evaluation methods in Taiwan to develop a new safety evaluation mechanism for the highway bus industry. This paper introduces a two-stage decision making approach that includes the use of fuzzy analytic hierarchy process (Fuzzy AHP) and machine learning techniques such as decision trees, support vector machines, and random forests to develop this mechanism. The data used in this research were collected from the internet and directly from highway bus transportation companies. We calculated the safety performance of each company and assigned them different safety ranks. Compared with the causes of accidents in Taiwan, the results of this study showed that work hours, driver fitness, and administrative penalties are the three most important sub-attributes that affect the safety rank of the company.
This study compares revealed versus stated household fuelwood preferences for particular tree species, explores the underlying factors, and discusses the implications for native forests. We used a cross-sectional survey of over 550 fuelwood consumers spanning rural areas to small, medium and large cities in the Los Lagos region of Chile conducted in 2020. We employed the Generalized Ordered Logit Model (GOLOGIT) and Multinomial Logit Model of household choice of major tree species for fuelwood. Our results show a significant misalignment between revealed and stated tree species preferences. Household tree species preferences for fuelwood is determined by fuel-value index (FVI), household expenditure, awareness of the relationship between fuelwood production and deforestation, and spatial heterogeneity. Household expenditure, as a proxy of family income, leads to selection of higher FVI tree species, though it is dependent on forest location and accessibility as well. As particular native species are those with high FVI, this implies a possible relationship between household income and native forest degradation that needs to be further explored. At the same time, awareness of deforestation is correlated with households buying the more abundant but less preferred species of fuelwood. These results point to potential impacts on native forests in Southern Chile, which will vary according to tree species´ecological characteristics, their regeneration potential, and harvesting methods used. Current policies incentivizing better thermal insulation of homes would allow people to use more abundant non-preferred tree species for fuelwood. These findings point to a need for continued research on how improved energy and forestry regulations can support more sustainable fuelwood consumption decisions within local fuelwood markets and better assessments of forest impacts of such policies.
For crash severity modeling, researchers typically view theory-driven models and data-driven models as different or even conflicting approaches. The reason is that the machine-learning models offer good predictability but weak interpretability, while the latter has robust interpretability but moderate predictability. In order to alleviate the tension between them, this study proposes an integrated data- and theory-driven crash-severity model, known as Embedded Fusion model based on Text Vector Representations (TVR-EF), by leveraging the complementary strengths of both. The model specification consists of two parts. (i) the data-driven component not only mitigate the deficiencies of traditional econometric models, where one-hot encoding is frequently used and makes it impossible to observe semantic relatedness between variable categories, but also enhances the interpretability for the relationship between crash severity and potential influencing factors using the learned embedding weight matrix. (ii) In the theory-driven component, the multinomial logit model is implemented as a 2D-Convolutional Neural Network (2D-CNN) to increase flexibility and decrease dependency on prior knowledge for different crash-severity outcomes. A crash dataset from Guangdong Province, China, is utilized to estimate the TVR-EF model, which is then benchmarked against two traditional econometric models and three widely used machine-learning models. Results indicate that TVR-EF model does not only improve the predictive performance but also makes it easier to interpret.
Background:
Determining suburban area crashes' risk factors may allow for early and operative safety measures to find the main risk factors and moderating effects of crashes. Therefore, this paper has focused on a causal modeling framework.
Study design:
A cross-sectional study.
Methods:
In this study, 52524 suburban crashes were investigated from 2015 to 2016. The hybrid-random-forest-generalized-path-analysis technique (HRF-gPath) was used to extract the main variables and identify mediators and moderators.
Results:
This study analyzed 42 explanatory variables using a RF model, and it was found that collision type, distinct, driver misconduct, speed, license, prior cause, plaque description, vehicle maneuver, vehicle type, lighting, passenger presence, seatbelt use, and land use were significant factors. Further analysis using g-Path demonstrated the mediating and predicting roles of collision type, vehicle type, seatbelt use, and driver misconduct. The modified model fitted the data well, with statistical significance ( χ230 =81.29, P<0.001) and high values for comparative-fit-index and Tucker-Lewis-index exceeding 0.9, as well as a low root-mean-square-error-of-approximation of 0.031 (90% confidence interval: 0.030-0.032).
Conclusion:
The results of our study identified several significant variables, including collision type, vehicle type, seatbelt use, and driver misconduct, which played mediating and predicting roles. These findings provide valuable insights into the complex factors that contribute to collisions via a theoretical framework and can inform efforts to reduce their occurrence in the future.
Single-vehicle (SV) crash severity model considering spatiotemporal correlations has been extensively investigated, but spatiotemporal interactions have not received sufficient attention. This research is dedicated to propose a superior spatiotemporal interaction correlated random parameters logit approach with heterogeneity in means and variances (STICRP-logit-HMV) for systematically characterizing unobserved heterogeneity, spatiotemporal correlations, and spatiotemporal interactions. Four flexible interaction formulations are developed to uncover the spatiotemporal interactions, including linear structure, Kronecker product, mixture-2 model, and mixture-5 model. Four candidate approaches-random parameters logit (RP-logit), RP-logit with heterogeneity in means and variances (RP-logit-HMV), correlated RP-logit-HMV (CRP-logit-HMV), and spatiotemporal CRP-logit-HMV (STCRP-logit-HMV)-are also established and compared with the proposed model. SV crash observations in Shandong Province, China, are employed to calibrate regression parameters. The model comparison results show that (1) the performance of the RP-logit-HMV model outperforms the RP-logit model, implying that capturing heterogeneity in the means and variances can strengthen model fit; (2) the CRP-logit-HMV model and the RP-logit-HMV model are comparable; (3) the STCRP-logit-HMV model outperforms the CRP-logit-HMV model, implying that addressing the spatiotemporal crash mechanisms is beneficial to the overall fitting of the crash model; (4) the STICRP-logit-HMV model performs better than the STCRP-logit-HMV model and this finding remains stable across different interaction formulations, indicating that comprehensively reflecting the spatiotemporal correlations and their interactions is a promising approach to model SV crashes. Among the four interaction models, the STICRP-logit-HMV model with mixture-5 component maintains the best fit, which is a recommended approach to model crash severity. The regression coefficients for young driver, male driver, and non-dry road surface are random across observations, suggesting that the influence of these factors on SV crash severity maintains significant heterogeneity effects. The research results provide transportation professionals with a superior statistical framework for diagnosing crash severity, which is beneficial for improving traffic safety.
There is an ongoing debate among transport planners and safety policy makers as to whether there is any association between the level of traffic congestion and road safety. One can expect that the increased level of traffic congestion aids road safety and this is because average traffic speed is relatively low in a congested condition relative to an uncongested condition, which may result in less severe crashes. The relationship between congestion and safety may not be so straightforward, however, as there are a number of other factors such as traffic flow, driver characteristics, road geometry, and vehicle design affecting crash severity. Previous studies have employed count data models (either Poisson or negative binomials and their extensions) while developing a relationship between the frequency of traffic crashes and traffic flow or density (as a proxy for traffic congestion). The use of aggregated crash counts at a road segment level or at an area level with the proxy for congestion may obscure the actual relationship. The objective of this study is to explore the relationship between the severity of road crashes and the level of traffic congestion using disaggregated crash records and a measure of traffic congestion while controlling for other contributory factors. Ordered response models such as ordered logit models, heterogeneous choice models, and generalized ordered logit (partially constrained) models suitable for both ordinal dependent variables and disaggregate crash data are used. Data on crashes, traffic characteristics (e.g., congestion, flow, and speed), and road geometry (e.g., curvature and gradient) were collected from the M25 London orbital motorway between 2003 and 2006. Our results suggest that the level of traffic congestion does not affect the severity of road crashes on the M25 motorway. The impact of traffic flow on the severity of crashes, however, shows an interesting result. All other factors included in the models also provide results consistent with existing studies.
The Buses Involved in Fatal Accidents (BIFA) project collects detailed information about buses involved in fatal crashes. The BIFA project is supported by the Federal Motor Carrier Safety Administration. Using BIFA data for 1999 to 2005, this study focuses on factors associated with driver errors in fatal bus crashes involving different bus operator types. Five different carrier types were identified: school, transit, intercity, charter or tour, and other. Many factors were associated with driver error, including bus operation type, age, sex, hours driving, trip type, method of compensation, and previous driving record. A logistic regression model was used to model the probability of driver error. Bus operation type, previous violations, and previous crashes were significant parameters in the model. Prior driver violations and crashes both increased the probability that a driver would have been coded with an error in the crash. Transit and school bus drivers were the least likely to have contributed to the crash. Intercity operations were associated with an increase in the odds by 1.9 times, with a 95% confidence interval from 1.1 to 3.2 times. Charter and other bus operations were associated with significantly higher odds of driver error. The odds ratio for charter or tour bus operations was 1.7 (range of 1.2 to 2.4), and for other buses it was 2.6 (range of 1.9 to 3.6). The other factors were not significant.
Sleep problems and their direct consequence, sleepiness, results in critical effects on psychomotor skills, memory, decision making, concentration and learning; all of which may play roles in accidents and errors. Despite the importance of quality of sleep among drivers there are only few researches that deal with them. Therefore, we designed this research to better understand possible relationships. This cross-sectional study was performed between 2006 and 2007 among 175 bus drivers of a transportation company in Tehran, the capital of Iran. Participants filled out a questionnaire concerning their demographic and personal history, associated disease, the insomnia index, the Epworth sleepiness scale (ESS), and the apnea index. Then they elaborated their history of crashes. Data was analyzed with the SPSS software through χ(2), Oneway ANOVAs, and Pearson correlation tests. The mean age, and body mass index (BMI) were 43.47 ± 6.85 years and 26.35 ± 3.87 kg/m(2). The mean duration of sleep among these drivers was 6.37 ± 1.62 h per day. The mean accident rate was 2.31 ± 1.83 per year. There was a significant correlation between the insomnia index and BMI (P = 0.014), age (0.00), marital status (0.00), associated disease (0.005), and drug history (0.028). There was a significant relationship between marital status and the ESS, and also between age and accident rate in the past years. Sleep problems were a frequent finding among the studied group and had a significant relationship with their crash history. These results can be an alarming sign to choose bus drivers more carefully and pay more attention to treating their sleep disorders.
This article describes the gologit2 program for generalized ordered logit models. gologit2 is inspired by Vincent Fu’s gologit routine (Stata Technical Bulletin Reprints 8: 160–164) and is backward compatible with it but offers several additional powerful options. A major strength of gologit2 is that it can fit three special cases of the generalized model: the proportional odds/parallel-lines model, the partial proportional odds model, and the logistic regression model. Hence, gologit2 can fit models that are less restrictive than the parallel-lines models fitted by ologit (whose assumptions are often violated) but more parsimonious and interpretable than those fitted by a nonordinal method, such as multinomial logistic regression (i.e., mlogit). Other key advantages of gologit2 include support for linear constraints, survey data estimation, and the computation of estimated probabilities via the predict command.
A number of accident characteristics of bus crashes are analyzed in relation to each other using data from 2237 accident involvements in the city of Uppsala (Sweden) during the years 1986-2000. The breakdown of accidents into sub-categories show, for example, that injury was common in intersection accidents, that bus stops present large risk for shunts and side contacts, while single vehicle accidents were seldom preceded by the loss of control or a skid. The treatment of accident data is discussed in terms of methodology, statistics and data reduction strategies.
Non-invasive mapping of brain structure and function with magnetic resonance imaging (MRI) has opened up unprecedented opportunities for studying the neural substrates underlying cognitive development. There is an emerging consensus of a continuous increase throughout adolescence in the volume of white matter, both global and local. There is less agreement on the meaning of asynchronous age-related decreases in the volume of grey matter in different cortical regions; these might equally represent loss ("pruning") or gain (intra-cortical myelination) of tissue. Functional MRI studies have so far focused mostly on executive functions, such as working memory and behavioural inhibition, with very few addressing questions regarding the maturation of social cognition. Future directions for research in this area are discussed in the context of processing biological motion and matching perceptions and actions.
Preface
Introduction
Transportation is integral to developed societies. It is responsible for personal mobility which includes access to services, goods, and leisure. It is also a key element in the delivery of consumer goods. Regional, state, national, and the world economy rely upon the efficient and safe functioning of transportation facilities.
In addition to the sweeping influence transportation has on economic and social aspects of modern society, transportation issues pose challenges to professionals across a wide range of disciplines including transportation engineers, urban and regional planners, economists, logisticians, systems and safety engineers, social scientists, law enforcement and security professionals, and consumer theorists. Where to place and expand transportation infrastructure, how to safely and efficiently operate and maintain infrastructure, and how to spend valuable resources to improve mobility, access to goods, services and healthcare, are among the decisions made routinely by transportation-related professionals.
Many transportation-related problems and challenges involve stochastic processes that are influenced by observed and unobserved factors in unknown ways. The stochastic nature of these problems is largely a result of the role that people play in transportation. Transportation-system users are routinely faced with decisions in contexts such as what transportation mode to use, which vehicle to purchase, whether or not to participate in a vanpool or telecommute, where to relocate a business, whether or not to support a proposed light-rail project and whether to utilize traveler information before or during a trip. These decisions involve various degrees of uncertainty. Transportation-system managers and governmental agencies face similar stochastic problems in determining how to measure and compare system measures of performance, where to invest in safety improvements, how to efficiently operate transportation systems and how to estimate transportation demand. As a result of the complexity, diversity, and stochastic nature of transportation problems, the methodological toolbox required of the transportation analyst must be broad.
Approach
The third edition of Statistical and Econometric Methods offers an expansion over the first and second editions in response to the recent methodological advancements in the fields of econometrics and statistics, to address reader and reviewer comments on the first and second editions, and to provide an increasing range of examples and corresponding data sets.
This book describes and illustrates some of the statistical and econometric tools commonly used in transportation data analysis. Every book must strike an appropriate balance between depth and breadth of theory and applications, given the intended audience. This book targets two general audiences. First, it can serve as a textbook for advanced undergraduate, Masters, and Ph.D. students in transportation-related disciplines including engineering, economics, urban and regional planning, and sociology. There is sufficient material to cover two 3-unit semester courses in statistical and econometric methods. Alternatively, a one semester course could consist of a subset of topics covered in this book. The publisher’s web-site contains the numerous datasets used to develop the examples in this book so that readers can use them to reinforce the modeling techniques discussed throughout the text. The book also serves as a technical reference for researchers and practitioners wishing to examine and understand a broad range of statistical and econometric tools required to study transportation problems. It provides a wide breadth of examples and case studies, covering applications in various aspects of transportation planning, engineering, safety, and economics. Sufficient analytical rigor is provided in each chapter so that fundamental concepts and principles are clear and numerous references are provided for those seeking additional technical details and applications.
Data-Driven Methods vs. Statistical and Econometric Methods
In the analysis of transportation data, four general methodological approaches have become widely applied: data-driven methods, traditional statistical methods, heterogeneity models, and causal inference models (the latter three of which fall into the category of statistical and econometric methods and are covered in this text). Each of these methods have an implicit trade-off between practical prediction accuracy and their ability to uncover underlying causality. Data-driven methods include a wide range of techniques including those relating to data mining, artificial intelligence, machine learning, neural networks, support vector machines, and others. Such methods have the potential to handle extremely large amounts of data and provide a high level of prediction accuracy. On the down side, such methods may not necessarily provide insights into underlying causality (truly understanding the effects of specific factors on accident likelihoods and their resulting injury probabilities). Traditional statistical methods provide reasonable predictive capability and some insight into causality, but they are eclipsed in both prediction and providing causal insights by other approaches Heterogeneity models extend traditional statistical and econometric methods to account for potential unobserved heterogeneity (unobserved factors that may be influencing the process of interest). Causal-inference models use statistical and econometric methods to focus on underlying causality, often sacrificing predictive capability to do so.
Even though data-driven methods are often a viable alternative to the analysis of transportation data if one is interested solely in prediction and not interested in uncovering causal effects, because the focus of this book is uncovering issues of causality using statistical and econometric methods, data-driven methods are not covered.
Chapter topics and organization
Part I of the book provides statistical fundamentals (Chapters 1 and 2). This portion of the book is useful for refreshing fundamentals and sufficiently preparing students for the following sections. This portion of the book is targeted for students who have taken a basic statistics course but have since forgotten many of the fundamentals and need a review.
Part II of the book presents continuous dependent variable models. The chapter on linear regression (Chapter 3) devotes additional pages to introduce common modeling practice—examining residuals, creating indicator variables, and building statistical models—and thus serves as a logical starting chapter for readers new to statistical modeling. The subsection on Tobit and censored regressions is new to the second edition. Chapter 4 discusses the impacts of failing to meet linear regression assumptions and presents corresponding solutions. Chapter 5 deals with simultaneous equation models and presents modeling methods appropriate when studying two or more interrelated dependent variables. Chapter 6 presents methods for analyzing panel data—data obtained from repeated observations on sampling units over time, such as household surveys conducted several times to a sample of households. When data are collected continuously over time, such as hourly, daily, weekly, or yearly, time series methods and models are often needed and are discussed in Chapters 7 and 8. New to the 2nd edition is explicit treatment of frequency domain time series analysis including Fourier and Wavelets analysis methods. Latent variable models, discussed in Chapter 9, are used when the dependent variable is not directly observable and is approximated with one or more surrogate variables. The final chapter in this section, Chapter 10, presents duration models, which are used to model time-until-event data as survival, hazard, and decay processes.
Part III in the book presents count and discrete dependent variable models. Count models (Chapter 11) arise when the data of interest are non-negative integers. Examples of such data include vehicles in a queue and the number of vehicle crashes per unit time. Zero inflation—a phenomenon observed frequently with count data—is discussed in detail and a new example and corresponding data set have been added in this 2nd edition. Logistic Regression is commonly used to model probabilities of binary outcomes, is presented in Chapter 12, and is unique to the 2nd edition. Discrete outcome models are extremely useful in many study applications, and are described in detail in Chapter 13. A unique feature of the book is that discrete outcome models are first considered statistically, and then later related to economic theories of consumer choice. Ordered probability models (a new chapter for the second edition) are presented in Chapter 14. Discrete-continuous models are presented in Chapter 15 and demonstrate that interrelated discrete and continuous data need to be modeled as a system rather than individually, such as the choice of which vehicle to drive and how far it will be driven.
Finally, Part IV of the book contains massively expanded chapter on random parameters models (Chapter 16), a new chapter on latent class models (Chapter 17), a new chapter on bivariate and multivariate dependent variable models (Chapter 18) and an expanded chapter on Bayesian statistical modeling (Chapter 19). Models that deal with unobserved heterogeneity (random parameters models and latent class models) have become the standard statistical approach in many transportation sub-disciplines and Chapters 16 and 17 provide an important introduction to these methods. Bivariate and multivariate dependent variable models are encountered in many transportation data analyses. Although the inter-relation among dependent variables has often been ignored in transportation research, the methodologies presented in Chapter 18 show how such inter-dependencies can be accurately modeled. The chapter on Bayesian statistical models (Chapter 19) arises as a result of the increasing prevalence of Bayesian inference and Markov Chain Monte Carlo Methods (an analytically convenient method for estimating complex Bayes’ models). This chapter presents the basic theory of Bayesian models, of Markov Chain Monte Carlo methods of sampling, and presents two separate examples of Bayes’ models.
The appendices are complementary to the remainder of the book. Appendix A presents fundamental concepts in statistics which support analytical methods discussed. Appendix B provides tables of probability distributions used in the book, while Appendix C describes typical uses of data transformations common to many statistical methods.
While the book covers a wide variety of analytical tools for improving the quality of research, it does not attempt to teach all elements of the research process. Specifically, the development and selection of research hypotheses, alternative experimental design methodologies, the virtues and drawbacks of experimental versus observational studies, and issues involved with the collection of data are not discussed. These issues are critical elements in the conduct of research, and can drastically impact the overall results and quality of the research endeavor. It is considered a prerequisite that readers of this book are educated and informed on these critical research elements in order to appropriately apply the analytical tools presented herein.
Simon P. Washnington
Mathew G. Karlaftis
Fred L. Mannering
Panigiotis Ch. Anastasopoulos
The objective of the research presented here was to capture the relationship between public transit service configurations and the overall safety performance of signalized intersections in Toronto, Ontario, Canada. Negative binomial regression models were developed for this purpose for three sets of dependent variables: transit-involved collisions at signalized intersections with both regular traffic and transit service operations; total collisions at the same signalized intersections; and total collisions at all signalized intersections, including those without transit service. The models showed that annual average daily traffic, public transit and pedestrian traffic volumes, turn movement treatments, and transit features (such as public transit stop location, mode technology, and availability of transit signal priority technology) all have significant associations with public transit–related collisions at signalized intersections. Intersections with public transit service also tend to experience more collisions than otherwise similar intersections. The research helps to address intersection safety from two perspectives: (a) it enables public transit providers to consider safety implications in the service planning process, and (b) it enables transportation departments to assess signalized intersection safety for various configurations of surface transit services by taking into consideration their interaction with the general traffic stream.
Through its National Center for Transit Research, and under contract with the Florida Department of Transportation, the Center for Urban Transportation Research (CUTR) was tasked with reviewing a sample of data on transit bus crash occurrence from selected Florida transit systems. The purpose of this review is to analyze changes in crash occurrence over time in relation to the effectiveness of training programs and capital safety improvements in reducing bus crashes. To this end, CUTR conducted two case studies utilizing occurrence data from Hillsborough Area Regional Transit Authority in Tampa (which implemented a refresher training course for bus operators) and LYNX Transit in Orlando (which replaced standard rear-end brake lights and turn signal and emergency flasher lights with high-density LED lights). The case studies examined the effect that these two particular safety campaigns had on postimplementation bus crash occurrence for the two properties. In addition to the promotion of safety, it is anticipated that this effort will be a preliminary step in the process of establishing a general list of safety campaigns, along with related costs and "rule of thumb" occurrence prevention effectiveness levels for each. A list of this nature will aid transit systems in Florida, the United States, and elsewhere in the selection of safety campaigns that will meet financial and safety goals.
The influences of heat and rain upon accident risk of city buses in a Swedish town were studied for a 10-year time period, but no reliable effects found, despite the fact that the temperature might be as high as 30°C outside the vehicles. As the use of single accidents with buses bypasses many of the methodological problems inherent in the study of weather effects on accident rates, for example changes in general traffic density, the present study was a rather strict test of the hypothesis of increased accident risk due to these factors. It was therefore concluded that rain and high temperatures do not increase the risk of accident for low-speed buses in Sweden. However, there could still be an effect of hot weather on bus accidents at higher temperatures than those normally found in Sweden.
Predictions about effects of aggregating driver celeration data were tested in a set of data where bus drivers’ behavior had been measured repeatedly over three years in a city environment. For drivers with many measurements, this data was correlated with the drivers’ accident record at various levels of aggregation over measurements. A single measurement (one sample) was seldom a significant predictor, but for each drive added to a mean, the variation explained in accident record was increased by about 1%. Also, correlations between measurements increased when these were aggregated, and the association with number of passengers (a proxy for traffic density) decreased somewhat, all as predicted. These results show that although driver celeration behavior is only semi-stable across time and environments, aggregating measurements increases both stability and predictive power versus accidents considerably. The celeration variable is therefore promising as a tool for identifying dangerous drivers, if these can be measured repeatedly, or, even better, continuously.
This study was undertaken to explore the factors affecting the safety performance of bus companies in Taiwan. A conceptual framework was developed based on the theory of organizational accidents. Environmental and organizational factors were assumed to determine the safety performance of bus companies. Since the deregulation of intercity passenger transportation in 1995 the bus transportation industry in Taiwan has been restructured, and this provides an opportunity to gain insight into the factors that influence the safety performance of bus companies. The study results show that the bus companies on joining intercity bus services in Taiwan did experience higher risks of being involved in major injury and minor injury accidents. The study results provide convincing evidence that organizational factors, including driver-specific, vehicle-specific and general management factors, have significant effects on the safety performance of bus companies. Therefore, if the economic deregulation was implemented with some safety regulation policies, we might have the opportunity to pursue a better safety performance by the bus transport industry as a whole, rather than just prevent the deterioration of the existing safety performance. Furthermore, the limited resources available to monitor the safety performance of bus companies are suggested to focus on those companies that run intercity services as well as those companies of small size, having older fleets, and a higher traffic conviction rate.
The effects of training in fuel-efficient driving for bus drivers in a city environment were evaluated. Three dependent variables, hypothetically associated with such training, were used; fuel and accident data from the bus company, and driver acceleration behavior from five buses, over time periods of several years. Effects of temperature and number of passengers on fuel consumption were held constant. Fuelling and acceleration data yielded fairly similar results. It was found that, although the effects on these variables during training were very strong (as found in a previous study), these did not transfer well into the drivers’ working situation. Overall, the effect was about two percent fuel consumption reduction as a mean over 12 months after training. No effect was found for accidents, although a two percent reduction would not have been detectable. In a second phase of the study, 28 buses were equipped with Econen feedback equipment, which give an indication on how much fuel is used concurrently, resulting in a further reduction of consumption of about two percent.
This paper develops a model, with assumptions similar to those of the linear model, for use when the observed dependent variable is ordinal. This model is an extension of the dichotomous probit model, and assumes that the ordinal nature of the observed dependent variable is due to methodological limitations in collecting the data, which force the researcher to lump together and identify various portions of an (otherwise) interval level variable. The model assumes a linear eflect of each independent variable as well as a series of break points between categories for the dependent variable. Maximum likelihood estimators are found for these parameters, along with their asymptotic sampling distributions, and an analogue of R (the coefficient of determination in regression analysis) is defined to measure goodness of fit. The use of the model is illustrated with an analysis of Congressional voting on the 1965 Medicare Bill.
Unlike in developed countries where buses are a relatively safe mode of transport, there is a significant safety concern in many developing countries like Bangladesh regarding transit buses. Nevertheless, few studies have examined the factors contributing to the number or severity of bus crashes. Using the ordered probit model on bus crash data from 1998 to 2005 in Dhaka, Bangladesh, our study shows that there is a general increase in the severity of transit bus crashes over this period. Also, crash severity tends to increase when the collision occurs on weekends, off-peak periods, and two-way streets or involves only one vehicle, a pedestrian, and other vulnerable road users. On the other hand, the severity of a crash tends to be lower at locations with some form of police control or road medians, as well as for crashes involving hit object, parked vehicles, or sideswipes. Copyright © 2010 John Wiley & Sons, Ltd.
This study uses a crash specific data set that is supplemented with location based socioeconomic data to estimate the impact of driver alcohol use on average crash severity. Logit estimates indicate that crashes in which the at-fault drivers had been drinking are more likely to result in a severe injury or death than are crashes caused by sober drivers. Ordered logit estimates indicate that at-fault driver alcohol use increases the expected highest degree of injury resulting from a crash, and Tobit estimates indicate that the number of injuries or deaths per crash increase an average of 0.71 when the at-fault driver has been drinking. Moreover, at-fault driver alcohol use worsens the severity of crashes relative to not-at-fault parties. Collectively, these results indicate that at-fault drinking drivers are involved in more violent crashes and produce more serious injuries to not-at-fault parties than at-fault sober drivers.
This paper presents a parameter covariance matrix estimator which is consistent even when the disturbances of a linear regression model are heteroskedastic. This estimator does not depend on a formal model of the structure of the heteroskedasticity. By comparing the elements of the new estimator to those of the usual covariance estimator, one obtains a direct test for heteroskedasticity, since in the absence of heteroskedasticity, the two estimators will be approximately equal, but will generally diverge otherwise. The test has an appealing least squares interpretation.
This paper evaluates roadway and operational factors considered to influence crashes involving buses. Factors evaluated included those related to bus sizes and operation services. Negative binomial (NB) and multinomial logit (MNL) models were used in linearizing and quantifying these factors with respect to crash frequency and injury severities, respectively. The results showed that position of the bus travel lane, presence or absence of on-street shoulder parking, posted speed limit, lane width, median width, number of lanes per direction and number of vehicles per lane has a higher influence on bus crashes compared to other roadway and traffic factors. Wider lanes and medians were found to reduce probability of bus crashes while more lanes and higher volume per lane were found to increase the likelihood of occurrences of bus-related crashes. Roadways with higher posted speed limits excluding freeways were found to have high probability of crashes compared to low speed limit roadways. Buses traveling on the inner lanes and making left turns were found to have higher probability of crashes compared to those traveling on the right most lanes. The same factors were found to influence injury severity though with varying magnitudes compared to crash frequency.
Pedestrian-injury severity has been traditionally modeled with approaches that have assumed that the effect of each variable is fixed across injury observations. This assumption ignores possible unobserved heterogeneity which is likely to be particularly important in pedestrian injuries because unobserved physical health, strength, and behavior may significantly affect the pedestrians' ability to absorb collision forces. To address such unobserved heterogeneity, this research applies a mixed logit model to analyze pedestrian-injury severity in pedestrian-vehicle crashes. Using police-reported collision data from 1997 through 2000 from North Carolina, several factors were found to more than double the average probability of fatal injury for pedestrians in motor-vehicle crashes including: darkness without streetlights (400% increase in fatality probability), vehicle is a truck (370% increase), freeway (330% increase), speeding involved (360% increase), and collisions involving a motorist who had been drinking (250% increase). It was also found that the effect of pedestrian age was normally distributed across observations, and that as pedestrians became older the probability of fatal injury increased substantially. Heterogeneity in the mean of the random parameters for the freeway and pedestrian-solely-at-fault collision indicators was related to pedestrian gender, and heterogeneity in the mean of the random parameters for the traffic-sign and motorist-back-up indicators was related to pedestrian age.
With baby boomers reaching retirement age, Western countries may need more immigrant workers to ensure productivity. Many studies have suggested a higher occupational injury frequency among immigrant workers, which could considerably reduce their contribution to society. The aim of this study was to examine whether immigrant workers have a higher injury frequency compared to Finnish workers when performing the exact same tasks under the same working conditions.
A total of 176 Finnish and 130 immigrant bus drivers were asked about their occupational injuries during the past 12 months via a questionnaire. In addition, the data contained 134 injuries reported by the transport firm to an insurance company.
There was no significant difference in reporting occupational injuries by self-reporting or by company-records. Because there were more accident-repeaters among Finnish drivers, their injury frequency (114) was higher than that of immigrant drivers (78). APPLICATION/IMPACT: This study showed that immigrant workers did not have a higher injury frequency than other workers when they worked in the exact same conditions. Immigrant workers can work as safely as native-Finnish workers, when their working conditions and job contracts are at the same level as those of the original population. Immigrant workers can compensate for the shortage of workforce caused by an aging population.
Various indicators of health have been shown to be associated with traffic crash involvement. As general health is also related to absence from work, the latter variable may be more strongly related to crashes, especially for professional drivers.
Bus driver absence from work was analyzed in association with their crash records. Two British samples and one Swedish sample were used.
One of the British samples yielded fair correlations between crash record and absence, while for the other the effect was restricted to the first three months of driving. The Swedish data had effects in the expected direction but these were not significant.
The use of an indirect, overall measurement of health, may be a viable method for predicting the traffic crash involvement for professional drivers, although replications are needed in larger samples and other populations.
The use of absence records for the identification of at risk drivers would seem to be a simple and useful method for companies with major fleets, and it also shows the importance of promoting employee health and well being at work as a potential method of reducing the cost, not only of absenteeism, but also of crashes in company vehicles.
To explore the effects of working conditions of private-bus drivers on bus crashes in Kandy district, Sri Lanka.
A case-control study was carried out from August to September 2006. All private-bus drivers registered in Kandy district and involved in crashes reported to the police between November 2005 and April 2006 (n = 63) were selected as cases. Two control groups were included: private-bus drivers working on the same routes as the case drivers (n = 90) and private-bus drivers selected randomly from other routes of the district (n = 111). Data were collected using an anonymous self-administered questionnaire. Associations between working conditions and crashes were analysed using logistic regression.
A strong association was observed between drivers' disagreements about working hours and bus crashes (matched controls, adjusted odds ratio (AOR) 5.98, 95% CI 1.02 to 34.90; unmatched controls, AOR 18.74, 95% CI 2.00 to 175.84). A significant association was also observed between low salaries (<US$100) and private-bus crashes (matched controls, AOR 1.01, 95% CI 0.40 to 2.54; unmatched controls, AOR 3.09, 95% CI 1.26 to 7.57).
Drivers' disagreements about working hours and low salaries were significant risk factors for private-bus crashes in Kandy district, Sri Lanka. Therefore, new legislation for private-bus owners on the working hours and salaries of their drivers to prevent private-bus crashes is recommended.
Studies of school bus crashes have focused on the biomechanics of catastrophic collisions, with very few examining crash incidence.
Crashes in the state of Iowa were examined from January 2002 through December 2005. School bus crashes were identified through the Iowa Crash Data, a comprehensive database of all reported crashes in the State of Iowa. School bus mileage data were provided by the Iowa Department of Education. School bus crash, fatality, and injury rates were calculated and differences in crash and injury characteristics between school buses and other vehicles were examined.
The school bus crash, fatality and non-fatal injury rates were 320.7, 0.4 and 13.6 per 100 million bus miles travelled, respectively. School bus crash fatality and injury rates were 3.5 and 5.4 times lower than overall all vehicle crash fatality and injury rates, respectively. Drivers of other vehicles were more likely to have caused the crash than the bus driver (P<0.001).
School buses experience low crash rates, and the majority of crashes do not lead to injury. Buses are among the safest forms of road transportation, and efforts to educate drivers of other vehicles may help reduce crashes with buses.
Taking evasive actions vis-à-vis critical traffic situations impending to motor vehicle crashes endows drivers an opportunity to avoid the crash occurrence or at least diminish its severity. This study explores the drivers, vehicles, and environments' characteristics associated with crash avoidance maneuvers (i.e., evasive actions or no evasive actions). Rear-end collisions, head-on collisions, and angle collisions are analyzed separately using decision trees and the significance of the variables on the binary response variable (evasive actions or no evasive actions) is determined. Moreover, the random forests method is employed to rank the importance of the drivers/vehicles/environments characteristics on crash avoidance maneuvers. According to the exploratory analyses' results, drivers' visibility obstruction, drivers' physical impairment, drivers' distraction are associated with crash avoidance maneuvers in all three types of accidents. Moreover, speed limit is associated with rear-end collisions' avoidance maneuvers and vehicle type is correlated with head-on collisions and angle collisions' avoidance maneuvers. It is recommended that future research investigates further the explored trends (e.g., physically impaired drivers, visibility obstruction) using driving simulators which may help in legislative initiatives and in-vehicle technology recommendations.
The purpose of this study is to examine left-turn crash injury severity. Left-turning traffic colliding with opposing through traffic and with near-side through traffic are the two most frequently occurring conflicting patterns among left-turn crashes (Patterns 5 and 8 in the paper, respectively), and they are prone to be severe. Ordered probability models with either logit or probit function is commonly applied in crash injury severity analyses; however, its critical assumption that the slope coefficients do not vary over different alternatives except the cut-off points is usually too restrictive. Partial proportional odds models are generalizations of ordered probability models, for which some of the beta coefficients can differ across alternatives, were applied to investigate Patterns 5 and 8, and the total left-turn crash injuries. The results show that partial proportional odds models consistently perform better than ordered probability models. By focusing on specific conflicting patterns, locating crashes to the exact crash sites and relating approach variables to crash injury in the analysis, researchers are able to investigate how these variables affect left-turn crash injuries. For example, opposing through traffic and near-side crossing through traffic in the hour of collision were identified significant for Patterns 5 and 8 crash injuries, respectively. Protected left-turn phasing is significantly correlated with Pattern 5 crash injury. Many other variables in driver attributes, vehicular characteristics, roadway geometry design, environmental factors, and crash characteristics were identified. Specifically, the use of the partial proportional formulation allows a much better identification of the increasing effect of alcohol and/or drug use on crash injury severity, which previously was masked using the conventional ordered probability models.
The proportional odds model for ordinal logistic regression provides a useful extension of the binary logistic model to situations where the response variable takes on values in a set of ordered categories. The model may be represented by a series of logistic regressions for dependent binary variables, with common regression parameters reflecting the proportional odds assumption. Key to the valid application of the model is the assessment of the proportionality assumption. An approach is described arising from comparisons of the separate (correlated) fits to the binary logistic models underlying the overall model. Based on asymptotic distributional results, formal goodness-of-fit measures are constructed to supplement informal comparisons of the different fits. A number of proposals, including application of bootstrap simulation, are discussed and illustrated with a data example.
The impact that large trucks have on accident severity has long been a concern in the accident analysis literature. One important measure of accident severity is the most severely injured occupant in the vehicle. Such data are routinely collected in state accident data files in the U.S. Among the many risk factors that determine the most severe level of injury sustained by vehicle occupants, the number of occupants in the vehicle is an important factor. These effects can be significant because vehicles with higher occupancies have an increased likelihood of having someone seriously injured. This paper studies the occupancy/injury severity relationship using Washington State accident data. The effects of large trucks, which are shown to have a significant impact on the most severely injured vehicle occupant, are accounted for by separately estimating nested logit models for truck-involved accidents and for non-truck-involved accidents. The estimation results uncover important relationships between various risk factors and occupant injury. In addition, by comparing the accident characteristics between truck-involved accidents and non-truck-involved accidents, the risk factors unique to large trucks are identified along with the relative importance of such factors. The findings of this study demonstrate that nested logit modeling, which is able to take into account vehicle occupancy effects and identify a broad range of factors that influence occupant injury, is a promising methodological approach.
This paper describes the use of ordered probit models to examine the risk of different injury levels sustained under all crash types, two-vehicle crashes, and single-vehicle crashes. The results suggest that pickups and sport utility vehicles are less safe than passenger cars under single-vehicle crash conditions. In two-vehicle crashes, however, these vehicle types are associated with less severe injuries for their drivers and more severe injuries for occupants of their collision partners. Other conclusions also are presented; for example. the results indicate that males and younger drivers in newer vehicles at lower speeds sustain less severe injuries.
The reliability over time of a method for measuring driver acceleration behavior was tested on bus drivers in regular traffic. Also, a replication of an earlier finding of a correlation between driver acceleration behavior and accident frequency for the individual drivers was made. It was found that the split-half correlation is probably around 0.50 for the mean (of accelerations) of a 30-min drive, and similar for the test-retest of 2.5h measured about a month apart. With such reliability, the sample was probably too small to reliably determine any association with accidents, but some significant correlations were found. Some ways of holding constant the differences in exposure and driving environment were tried with mixed success. Alternate ways of analyzing the data and several methodological problems were briefly discussed. It was concluded that the measurements of acceleration behavior, for bus drivers, are fairly reliable over at least a few months. However, some strange discrepancies between samples make all interpretations concerning the link to accidents tentative.
My colleagues and I studied alcohol and illicit drug intoxication in trauma fatalities and their association with the nature and severity of injuries.
We examined the trauma registry and autopsies of all trauma fatalities at an academic Level I trauma center. Statistical analysis was performed to evaluate the association of substance use with the Injury Severity Score, body areas with severe trauma (Abbreviated Injury Score >/= 3), and spinal injuries.
From January 2000 to May 2003, 931 trauma deaths occurred; 600 victims were tested for alcohol and illicit drugs and 256 of these (42.7%) tested positive. Male victims were significantly more likely to have a positive screen than female patients (46.1% versus 26.7%, p = 0.0003). Penetrating trauma was significantly more likely to be associated with a positive screen than blunt trauma (53.0% versus 31.0%, p < 0.001). Hispanic and African-American victims were more likely to have a positive screen than Caucasians or Asians. Half the patients in the age group 15 to 50 years had a positive screen. Victims with penetrating trauma and positive screen were significantly more likely to be dead at hospital arrival than victims with negative toxicology (68.8% versus 48.8%, p = 0.05). Pedestrians killed by automobiles who had positive screens were more likely to have severe abdominal trauma (Abbreviated Injury Score >/= 3) than victims with negative toxicology (54.2% versus 25.0%, p = 0.02).
There is a high rate of alcohol and illicit drug use in patients who die from trauma, especially penetrating trauma in men aged 15 to 50 years, who are Hispanic or African American. Victims with penetrating trauma and positive toxicology are considerably more likely to have no vital signs on admission than victims with negative toxicology. Pedestrians killed by automobiles who had positive screens have a higher incidence of severe abdominal injuries than victims with negative screens.
This study explores the differences between urban and rural driver injuries (both passenger-vehicle and large-truck driver injuries) in accidents that involve large trucks (in excess of 10,000 pounds). Using 4 years of California accident data, and considering four driver-injury severity categories (no injury, complaint of pain, visible injury, and severe/fatal injury), a multinomial logit analysis of the data was conducted. Significant differences with respect to various risk factors including driver, vehicle, environmental, road geometry and traffic characteristics were found to exist between urban and rural models. For example, in rural accidents involving tractor-trailer combinations, the probability of drivers' injuries being severe/fatal increased about 26% relative to accidents involving single-unit trucks. In urban areas, this same probability increased nearly 700%. In accidents where alcohol or drug use was identified as being the primary cause of the accident, the probability of severe/fatal injury increased roughly 250% percent in rural areas and nearly 800% in urban areas. While many of the same variables were found to be significant in both rural and urban models (although often with quite different impact), there were 13 variables that significantly influenced driver-injury severity in rural but not urban areas, and 17 variables that significantly influenced driver-injury severity in urban but not rural areas. We speculate that the significant differences between rural and urban injury severities may be at least partially attributable to the different perceptual, cognitive and response demands placed on drivers in rural versus urban areas.
The driver celeration behavior theory predicts that celerations are associated with incidents for which the driver has some responsibility in causing, but not other incidents.
The hypothesis was tested in 25 samples of repeated measurements of bus drivers' celeration behavior against their incidents for two years.
The results confirmed the prediction; in 18 samples, the correlation for culpable incidents only was higher than for all incidents, despite the higher means of the latter. Non-culpable incidents had correlations close to zero with celeration.
It was pointed out that most individual crash prediction studies have not made this differentiation, and thus probably yielded underestimates of the associations sought, although the effect is not strong, due to non-culpable accident involvements being few (less than a third of the total). The methods for correct identification of culpable incident involvements were discussed.
Strategy for integrating environment and sustainable de-velopment into the transport policy. http://corporate.skynet.be/sustainablefreight/ trans-counci-conclusion-05-04-01 Estimating generalized ordered logit models
- Eu
- Ministers Council
- V Fu
EU Council of Ministers (2001). Strategy for integrating environment and sustainable de-velopment into the transport policy. http://corporate.skynet.be/sustainablefreight/ trans-counci-conclusion-05-04-01.htm Fu, V. (1998). Estimating generalized ordered logit models. Stata Technical Bulletin, 44, 27–30 (Stata technical bulletin reprints, Vol. 8, Stata Press, College Station, TX., 160–164).
Most wanted list – Bus occupant safety Mapping brain maturation and cognitive development during adoles-cence
- Dc Washington
- Author
Washington, DC: Author. National Transportation Safety Board (2011). Most wanted list – Bus occupant safety. http://www.ntsb.gov/safety/mwl.html Paus, T. (2005). Mapping brain maturation and cognitive development during adoles-cence. Trends in Cognitive Sciences, 9(2), 60–68.
Injury risks in collisions involving buses in Al-berta Urban bus drivers' sleep problems and crash ac-cidents
- M Rahman
- L Kattan
- R Tay
- D C Razmpa
- E Niat
- K S Saedi
Rahman, M., Kattan, L., & Tay, R. (2011). Injury risks in collisions involving buses in Al-berta. Proceedings of the 90th Annual Meeting of the Transportation Research Board, Washington, D.C. Razmpa, E., Niat, K. S., & Saedi, B. (2011). Urban bus drivers' sleep problems and crash ac-cidents. Indian Journal of Otolaryngology and Head and Neck Surgery, 63(3), 269–273.