A copula-based approach for jointly modeling crash severity and number of vehicles involved in express bus crashes on expressways considering temporal stability of data

Examining drivers injury severity for manual and automatic transmission vehicles-involved crashes: Random parameter mixed logit model with heterogeneity in means and variances

The effect of vehicle transmission type on driver injury severities have not been thoroughly studied. The study used four-year historical crash data that occurred between the year 2019 and 2022 in Ghana. The data shows 1856 and 2272 crashes for automatic and manual transmission, respectively. The study examined the factors influencing driver injury severity in crashes involving vehicles with manual and automatic transmissions, using Random Parameter Mixed Logit Model to account for heterogeneity in the dataset. It was observed that use of manual transmission is related to a higher risk of incapacitating and fatal injuries compared to automatic transmission. Specifically, for automatic transmission vehicle-involved crashes, factors related to fatal injury were overaged vehicles, public transport, morning and evening peak hours, head-on and rollover crashes. Crashes involving saloon cars and low age cars were associated with incapacitating injury whiles rainy weather condition was related to both fatal and incapacitant injuries. Regarding manual transmission, fatal injury was associated with crashes involving male and novice drivers, cars, pickup trucks, HGV, public transports, morning and evening peak hours, rainy weather conditions and curved roads. Also, buses, private cars and trip distance were related to incapacitating injury. The rollover crashes and overaged vehicles were also associated with both fatal and incapacitating injuries. Four random parameters demonstrated heterogeneity in means, with two factors influencing the variances of two parameters for automatic transmission model. For the manual transmission model, five random parameters showed heterogeneity in means, with four variables influencing the variances of three parameters. These findings are valuable for policymakers, manufacturers, and drivers in implementing targeted interventions and safety measures to promote road safety.

Stability of factors influencing walking-along-the-road pedestrian injury severity outcomes under different lighting conditions: A random parameters logit approach with heterogeneity in means and out-of-sample predictions

Pedestrians walking along the road's edge are more exposed and vulnerable than those on designated crosswalks. Often, they remain oblivious to the imminent perils of potential collisions with vehicles, making crashes involving these pedestrians relatively unique compared to others. While previous research has recognized that the surrounding lighting conditions influence traffic crashes, the effect of different lighting conditions on walking-along-the-road pedestrian injury severity outcomes remains unexplored. This study examines the variations in the impact of risk factors on walking-along-the-road pedestrian-involved crash injury severity across various lighting conditions. Preliminary stability tests on the walking-along-the-road pedestrian-involved crash data obtained from Ghana revealed that the effect of most risk factors on injury severity outcomes is likely to differ under each lighting condition, warranting the estimation of separate models for each lighting condition. Thus, the data were grouped based on the lighting conditions, and different models were estimated employing the random parameter logit model with heterogeneity in the means approach to capture different levels of unobserved heterogeneity in the crash data. From the results, heavy vehicles, shoulder presence, and aged drivers were found to cause fatal pedestrian walking-along-the-road severity outcomes during daylight conditions, indicators for male pedestrians and speeding were identified to have stronger associations with fatalities on roads with no light at night, and crashes occurring on Tuesdays and Wednesdays were likely to be severe on lit roads at night. From the marginal effect estimates, although some explanatory variables showed consistent effects across various lighting conditions in pedestrian walking-along-the-road crashes, such as pedestrians aged < 25 years and between 25 and 44 years exhibited significant variations in their impact across different lighting conditions, supporting the finding that the effect of risk factors are unstable. Further, the out-of-sample simulations underscored the shifts in factor effects between different lighting conditions, highlighting that enhancing visibility could play a pivotal role in significantly reducing fatalities associated with pedestrians walking along the road. Targeted engineering, education, and enforcement countermeasures are proposed from the interesting insights drawn to improve pedestrian safety locally and internationally.

Exploring Factors Affecting Crash Injury Severity with Consideration of Secondary Collisions in Freeway Tunnels

Although there have been several studies conducted exploring the factors affecting injury severity in tunnel crashes, most studies have focused on identifying factors that directly influence injury severity. In particular, variables related to crash characteristics and tunnel characteristics affect the injury severity, but the inconvenient driving environment in a tunnel space, characterized by narrow space and dark lighting, can affect crash characteristics such as secondary collisions, which in turn can affect the injury severity. Moreover, studies on secondary collisions in freeway tunnels are very limited. The objective of this study was to explore factors affecting injury severity with the consideration of secondary collisions in freeway tunnel crashes. To account for complex relationships between multiple exogenous variables and endogenous variables by considering the direct and indirect relationships between them, this study used a structural equation modeling with tunnel crash data obtained from Korean freeway tunnels from 2013 to 2017. Moreover, based on high-definition closed-circuit televisions installed every 250 m to monitor incidents in Korean freeway tunnels, this study utilized unique crash characteristics such as secondary collisions. As a result, we found that tunnel characteristics indirectly affected injury severity through crash characteristics. In addition, one variable regarding crashes involving drivers younger than 40 years old was associated with decreased injury severity. By contrast, ten variables exhibited a higher likelihood of severe injuries: crashes by male drivers, crashes by trucks, crashes in March, crashes under sunny weather conditions, crashes on dry surface conditions, crashes in interior zones, crashes in wider tunnels, crashes in longer tunnels, rear-end collisions, and secondary collisions with other vehicles.

Jointly analyzing freeway primary and secondary crash severity using a copula-based approach

A copula-based model is developed in this study to jointly model the severity of freeway primary crashes and secondary crashes. The copula-based model can concurrently account for the severity levels in the crash and the correlation among primary-secondary crash pairs' severity. The model comprehensively considers a series of explanation variables, including temporal characteristics, crash characteristics, roadway characteristics and real-traffic conditions, and is estimated using traffic crash data from 2016 through 2019 for Los Angeles County, California. The proposed copula model is then contrasted with the traditional binary probit model and the results show a remarkable advantage of the copula model, which is evidenced by better fitting performance. It is found that weather, whether towed away, unsafe speed, collision type, road condition, terrain, road weaving and truck involvement have significant impact on primary crash severity propensity and collision type, road width, road condition, traffic volume and vehicle speed have significant impact on secondary crash severity propensity. In light of the findings, a number of countermeasures are proposed to mitigate freeway crashes, including emergency services, vehicle and roadway engineering, traffic law enforcement and driver education.

Comparative Analysis of Influencing Factors on Crash Severity between Super Multi-Lane and Traditional Multi-Lane Freeways Considering Spatial Heterogeneity

With the growth of traffic demand, the number of newly built and renovated super multi-lane freeways (i.e., equal to or more than a two-way ten-lane) is increasing. Compared with traditional multi-lane freeways (i.e., a two-way six-lane or eight-lane), super multi-lane freeways have higher design speeds and more vehicle interweaving movements, which may lead to higher traffic risks. However, current studies mostly focus on the factors that affect crash severity on traditional multi-lane freeways, while little attention is paid to those on super multi-lane freeways. Therefore, this study aims to explore the impacting factors of crash severity on two kinds of freeways and make a comparison with traditional multi-lane freeways. The crash data of the Guangzhou-Shenzhen freeway in China from 2016 to 2019 is used in the study. This freeway contains both super multi-lane and traditional multi-lane road sections, and data on 2455 crashes on two-way ten-lane sections and 13,367 crashes on two-way six-lane sections were obtained for further analysis. Considering the effects of unobserved spatial heterogeneity, a hierarchical Bayesian approach is applied. The results show significant differences that influence the factors of serious crashes between these two kinds of freeways. On both two types of freeways, heavy-vehicle, two-vehicle, and multi-vehicle involvements are more likely to lead to serious crashes. Still, their impact on super multi-lane freeways is much stronger. In addition, for super multi-lane freeways, vehicle-to-facility collisions and rainy weather can result in a high possibility of serious crashes, but their impact on traditional multi-lane freeways are not significant. This study will contribute to understanding the impacting factors of crash severity on super multi-lane freeways and help the future design and safety management of super multi-lane freeways.

A Random-Parameter Negative Binomial Model for Assessing Freeway Crash Frequency by Injury Severity: Daytime versus Nighttime

This study explored the effects of contributing factors on crash frequency, by injury severity of all, daytime, and nighttime crashes that occurred on freeways. With three injury severity outcomes classified as light injury, minor injury, and severe injury, the effects of the explanatory variables affecting the crash frequency were examined in terms of the crash, traffic, speed, geometric, and sight characteristics. Regarding the model estimations, the lowest AIC and BIC values (2263.87 and 2379.22, respectively) showed the superiority of the random-parameter multivariate negative binomial (RPMNB) model in terms of the goodness-of-fit measure. Additionally, the RPMNB model indicated the highest R2 (0.25) and predictive accuracy, along with a significantly positive α parameter. Moreover, transferability tests were conducted to confirm the rationality of separating the daytime and nighttime crashes. Based on the RPMNB models, several explanatory variables were observed to exhibit relatively stable effects whereas other variables presented obvious variations. This study can be of certain value in guiding highway design and policies and developing effective safety countermeasures.

Mining groups of factors influencing bus/minibus crash severities on poor pavement condition roads considering different lighting status

OBJECTIVE

This study employs a data mining approach to discover hidden groups of crash-risk factors leading to each bus/minibus crash severity level on pothole-ridden/poor roads categorized under different lighting conditions namely daylight, night with streetlights turned on, and night with streetlights turned off/no streetlights.

METHODS

The bus/minibus data employed contained 2,832 crashes observed on poor roads between 2011 and 2015, with variables such as the weather, driver, vehicle, roadway, and temporal characteristics. The data was grouped into three based on lighting condition, and the association rule data mining approach was applied.

RESULTS

Overall, most rules pointing to fatal crashes included the hit-pedestrian variable, and these crashes were more frequent on straight/flat roads at night. While median presence was highly associated with severe bus/minibus crashes on dark-and-unlighted roads, median absence was correlated with severe crashes on dark-but-lighted roads. On-street parking was identified as a leading contributor to property-damage-only crashes in daylight conditions.

CONCLUSIONS

The study proposed relevant countermeasures to provide practical guidance to safety engineers regarding the mitigation of bus/minibus crashes in Ghana.

Temporal stability of associations between crash characteristics: A multiple correspondence analysis

Understanding the associations between crash characteristics facilitates the development of traffic safety policies for improving traffic safety. This study investigates the temporal stability of associations between crash characteristics at different temporal levels using multiple correspondence analysis (MCA). For each date in 2020, crash data from the previous week, month, season, half year, one year, two years, three years, and four years are collected respectively as eight temporal levels. MCA plots and chi-square distance analysis are used to assess the temporal stability of associations between crash characteristics across dates in 2020 with data from various temporal levels. The key findings of this study demonstrate that associations between crash characteristics at lower temporal levels show notable and potential cyclical variations across dates, while more stable and long-term trend of associations between crash characteristics may be identified as the temporal level increases, especially at the two-year level and higher temporal levels at which temporal stability may be expected. The study contributes to the literature by presenting a challenge for traffic analysts in that both temporally stable and unstable associations between crash characteristics may be observed at any point in time when different temporal levels are considered as study periods. Therefore, it may serve as a foundation for future research and practical works to identify traffic safety issues and optimal policies as well as facilitate the interpretation of statistical modeling in the presence of temporally unstable data.

Factors affecting motorcycle crash casualty severity at signalized and non-signalized intersections in Ghana: Insights from a data mining and binary logit regression approach

Despite the countless benefits derived from motorcycle usage, it has become a significant public health concern, particularly in developing countries, due to the plateauing number of fatal/serious injuries associated with them. Although it has been well documented that the frequency and fatality rates of intersection-related motorcycle crashes are high, little research efforts have been made to explore the contributory factors influencing motorcycle-involved crashes at these locations. Interestingly, no study has investigated the latent patterns and chains of factors that simultaneously contribute to the injury severity sustained by motorcycle crash casualties at intersections under different traffic control conditions in developing countries. Since motorcycles are mostly used as taxis in developing countries, it is imperative to consider the injury severity sustained by all crash casualties in the motorcycle safety analysis. This study bridges the research gap by employing a plausible data mining tool to explore hidden rules associated with motorcycle crash casualty injury severity outcomes at both signalized and non-signalized intersections in Ghana's most densely populated region, Accra, using three-year crash data spanning 2016-2018. Besides, a binary logit regression model was also employed to explore the impact of crash factors on casualty severity outcomes using the same dataset. The results from both analysis techniques were consistent; however, the data mining technique provided chains of factors which provided additional insights into the groups of factors that collectively influence the casualty injury severity outcomes. From the rule discovery results, while full license status, daytime/daylight, and shoulder presence increased the risk of fatal injuries at signalized intersections, factors such as inattentiveness, good road surface, nighttime, shoulder absence, and young rider were highly likely to increase casualty fatalities at non-signalized intersections. By controlling all or some of these risk factors, the level of injury severity on the roadways could be reduced. Based on the findings, we provide enforcement, education, and engineering-based recommendations to help improve motorcycle safety.

A resampling approach to disaggregate analysis of bus-involved crashes using panel data with excessive zeros

Public bus constitutes more than 70% of the overall road-based public transport patronage in Hong Kong, and its crash involvement rate has been the highest among all public transport modes. Though previous studies had identified explanatory factors that affect the crash risk of buses, use of considerably imbalanced crash data with excessive zero observations could lead to inaccurate parameter estimation. This study aims to resolve the excess zero problem of disaggregate analysis of bus-involved crashes based on synthetic data using a Synthetic Minority Over-Sampling Technique for panel data (SMOTE-P). Dataset comprising crash, traffic, and road inventory data of 88 road segments in Hong Kong during the period from 2014 to 2017 is used. To assess the data balancing performance, other common data generation approaches such as Random Under-sampling of the Majority Class (RUMC) technique, Cluster-Based Under-Sampling (CBUS), and mixed resampling, are also considered. Random effect Poisson (REP) models based on synthetic data and random effect zero-inflated Poisson (REZIP) model based on original data are estimated. Results indicate that REP model based on synthetic data using SMOTE-P outperforms REZIP model based on original data and REP models based on synthetic data using RUMC, CBUS and mixed approaches, in terms of statistical fit, prediction error, and explanatory factors identified. Results of model estimation based on SMOTE-P suggest that factors including morning peak, evening peak, hourly traffic flow, average lane width, road length, bus stop density, percentage of bus in the traffic stream, and presence of bus priority lane all affect the bus-involved crash frequency. More importantly, this study provides a feasible solution for disaggregate crash analysis with imbalanced panel data.

Bus Crash Severity in Hanoi, Vietnam

Recently, there has been an increasing interest in targeting the safety of bus operations worldwide; however, little is known about the determinants of the bus crash severity in developing countries. By estimating an ordered logit model using the bus-involved collision data in Hanoi (Vietnam), spanning the period from 2015 to 2019, this study investigates various factors associated with the crash severity. The results reveal that the severity risk increases for (1) large buses, (2) raining conditions, (3) evening or night, (4) sparse traffic, (5) non-urban areas, (6) roads with at least three lanes, (7) curved roads, (8) two-way roads without a physical barrier, (9) head-on collision, and (10) pedestrian-related crashes. Aside from confirming the crucial roles of a wide range of factors, this research has examined the effects of two determinants (traffic density and crash area) that have not been considered for the cases of developing countries previously. Based on the findings on the impacts of factors, a series of policy recommendations regarding improving road conditions in non-urban areas, promoting walking infrastructure, reminders of high-risk situations for drivers, safety notes when improving bus service quality, and recording bus-related crashes are proposed.

Investigating factors affecting bus/minibus accident severity in a developing country for different subgroup datasets characterised by time, pavement, and light conditions

Developing countries are primarily associated with poor roadway and lighting infrastructure challenges, which has a considerable effect on their traffic accident fatality rates. These rates are further increased as bus/minibus drivers indulge in risky driving, mainly during weekends when traffic and police surveillance is low to maximise profits. Although these factors have been mentioned in the literature as key indicators influencing accident severity of buses/minibuses, there is currently no study that explored the complex mechanisms underpinning the simultaneous effect of pavement and light conditions on the generation of accident severity outcomes while considering weekly temporal stability of the accident-risk factors. This study seeks to investigate the variations in the effect of contributing factors on the severity of bus/minibus accidents in Ghana across various combinations of pavement and light conditions and to identify the exact effects of weekdays and weekends on severity outcomes using a random parameter ordered logit model with heterogeneity in the means to account for unobserved heterogeneity in the police-reported data. Preliminary analysis demonstrated that accident-risk factors used in the models were temporally unstable, warranting the division of the data into both weekend and weekday time-periods. A wide variety of factors such as sideswipes, median presence, merging, and overtaking had significantly varying effects on bus/minibus accident severities under different combinations of pavement and light conditions for both weekdays and weekends. Insights drawn from this study, together with the policy recommendations provided, can be employed by engineers and policymakers to improve traffic safety in developing nations.

Fatal pedestrian crashes at intersections: Trend mining using association rules

In 2018, about 6,677 pedestrians were killed on the US roadways. Around one-fourth of these crashes happened at intersections or near intersection locations. This high death toll requires careful investigation. The purpose of this study is to provide an overview of the characteristics and associated crash scenarios resulting in fatal pedestrian crashes in the US. The current study collected five years (2014-2018) of fatal crash data with additional details of pedestrian crash typing. This dataset provides specifics of scenarios associated with fatal pedestrian crashes. This study applied associated rules mining on four sub-groups, which were determined based on the highest frequencies of fatal crash scenarios. This study also developed the top 20 rules for all four sub-groups and used 'a priori' algorithm with 'lift' as a performance measure. Some of the key variable categories such as dark with lighting condition, vehicle going straight, vehicle turning, local municipality streets, pedestrian age range from 45 years and above are frequently presented in the developed rules. The patterns of the rules differ by the pedestrian's position within and outside of crosswalk area. If the pedestrian is outside the crosswalk area, no lighting at dark is associated with high number of crashes. As lift provides quantitative measures in the form of the likelihood, the rules can be transferred into data-driven decision making. The findings of the current study can be used by safety engineers and planners to improve pedestrian safety at intersections.

Copula Models for Addressing Sample Selection in the Evaluation of Public Health Programmes: An Application to the Leeds Let's Get Active Study

Sample selectivity is a recurrent problem in public health programmes and poses serious challenges to their evaluation. Traditional approaches to handle sample selection tend to rely on restrictive assumptions. The aim of this paper is to illustrate a copula-based selection model to handle sample selection in the evaluation of public health programmes. Motivated by a public health programme to promote physical activity in Leeds (England), we describe the assumptions underlying the copula selection, and its relative advantages compared with commonly used approaches to handle sample selection, such as inverse probability weighting and Heckman's selection model. We illustrate the methods in the Leeds Let's Get Active programme and show the implications of method choice for estimating the effect on individual's physical activity. The programme was associated with increased physical activity overall, but the magnitude of its effect differed according to adjustment method. The copula selection model led to a similar effect to the Heckman's approach but with relatively narrower 95% confidence intervals. These results remained relatively similar when different model specifications and alternative distributional assumptions were considered. The copula selection model can address important limitations of traditional approaches to address sample selection, such as the Heckman model, and should be considered in the evaluation of public health programmes, where sample selection is likely to be present.