Analysis of left-turn crash injury severity by conflicting pattern using partial proportional odds models

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.     

Partial proportional odds model—An alternate choice for analyzing pedestrian crash injury severities

The conventional methods for crash injury severity analyses include either treating the severity data as ordered (e.g. ordered logit/probit models) or non-ordered (e.g. multinomial models). The ordered models require the data to meet proportional odds assumption, according to which the predictors can only have the same effect on different levels of the dependent variable, which is often not the case with crash injury severities. On the other hand, non-ordered analyses completely ignore the inherent hierarchical nature of crash injury severities. Therefore, treating the crash severity data as either ordered or non-ordered results in violating some of the key principles. To address these concerns, this paper explores the application of a partial proportional odds (PPO) model to bridge the gap between ordered and non-ordered severity modeling frameworks. The PPO model allows the covariates that meet the proportional odds assumption to affect different crash severity levels with the same magnitude; whereas the covariates that do not meet the proportional odds assumption can have different effects on different severity levels. This study is based on a five-year (2008–2012) national pedestrian safety dataset for Switzerland. A comparison between the application of PPO models, ordered logit models, and multinomial logit models for pedestrian injury severity evaluation is also included here. The study shows that PPO models outperform the other models considered based on different evaluation criteria. Hence, it is a viable method for analyzing pedestrian crash injury severities.     

Analysis of driver injury severity in rural single-vehicle crashes

Rural roads carry less than fifty percent of the traffic in the United States. However, more than half of the traffic accident fatalities occurred on rural roads. This research focuses on analyzing injury severities involving single-vehicle crashes on rural roads, utilizing a latent class logit (LCL) model. Similar to multinomial logit (MNL) models, the LCL model has the advantage of not restricting the coefficients of each explanatory variable in different severity functions to be the same, making it possible to identify the impacts of the same explanatory variable on different injury outcomes. In addition, its unique model structure allows the LCL model to better address issues pertinent to the independence from irrelevant alternatives (IIA) property. A MNL model is also included as the benchmark simply because of its popularity in injury severity modeling. The model fitting results of the MNL and LCL models are presented and discussed. Key injury severity impact factors are identified for rural single-vehicle crashes. Also, a comparison of the model fitting, analysis marginal effects, and prediction performance of the MNL and LCL models are conducted, suggesting that the LCL model may be another viable modeling alternative for crash-severity analysis.     

Analysis of large truck crash severity using heteroskedastic ordered probit models

Long-combination vehicles (LCVs) have significant potential to increase economic productivity for shippers and carriers by decreasing the number of truck trips, thus reducing costs. However, size and weight regulations, triggered by safety concerns and, in some cases, infrastructure investment concerns, have prevented large-scale adoption of such vehicles. Information on actual crash performance is needed. To this end, this work uses standard and heteroskedastic ordered probit models, along with the United States’ Large Truck Crash Causation Study, General Estimates System, and Vehicle Inventory and Use Survey data sets, to study the impact of vehicle, occupant, driver, and environmental characteristics on injury outcomes for those involved in crashes with heavy-duty trucks. Results suggest that the likelihood of fatalities and severe injury is estimated to rise with the number of trailers, but fall with the truck length and gross vehicle weight rating (GVWR). While findings suggest that fatality likelihood for two-trailer LCVs is higher than that of single-trailer non-LCVs and other trucks, controlling for exposure risk suggest that total crash costs of LCVs are lower (per vehicle-mile traveled) than those of other trucks.     

Analysis of injury severity of large truck crashes in work zones

Work zones are critical parts of the transportation infrastructure renewal process consisting of rehabilitation of roadways, maintenance, and utility work. Given the specific nature of a work zone (complex arrangements of traffic control devices and signs, narrow lanes, duration) a number of crashes occur with varying severities involving different vehicle sizes. In this paper we attempt to investigate the causal factors contributing to injury severity of large truck crashes in work zones. Considering the discrete nature of injury severity categories, a number of comparable econometric models were developed including multinomial logit (MNL), nested logit (NL), ordered logit (ORL), and generalized ordered logit (GORL) models. The MNL and NL models belong to the class of unordered discrete choice models and do not recognize the intrinsic ordinal nature of the injury severity data. The ORL and GORL models, on the other hand, belong to the ordered response framework that was specifically developed for handling ordinal dependent variables. Past literature did not find conclusive evidence in support of either framework. This study compared these alternate modeling frameworks for analyzing injury severity of crashes involving large trucks in work zones. The model estimation was undertaken by compiling a database of crashes that (1) involved large trucks and (2) occurred in work zones in the past 10 years in Minnesota. Empirical findings indicate that the GORL model provided superior data fit as compared to all the other models. Also, elasticity analysis was undertaken to quantify the magnitude of impact of different factors on work zone safety and the results of this analysis suggest the factors that increase the risk propensity of sustaining severe crashes in a work zone include crashes in the daytime, no control of access, higher speed limits, and crashes occurring on rural principal arterials.     

Predicting the severity of motor vehicle accident injuries using models of ordered multiple choice

This paper presents statistical evidence showing how variations in the attributes of road users can lead to variations in the probabilities of sustaining different levels of injury in motor vehicle accidents. Data from New South Wales, Australia, is used to estimate two models of multiple choice which are reasonably commonplace in the econometrics literature: the ordered logit model and the ordered probit model. Our estimated parameters are significantly different from zero at small levels of significance and have signs which are consistent with our prior beliefs. As a benchmark for comparison, we consider the risks faced by a 33-year old male driver of a 10-year-old motor vehicle who is involved in a head-on collision while travelling at 42 kilometres per hour. We estimate that this benchmark victim will remain uninjured with a probability of almost zero, will require treatment from a medical officer with a probability of approximately 0.7, will be admitted to hospital with a probability of approximately 0.3, and will be killed with a probability of almost zero. We find that increases in the age of the victim and vehicle speed lead to slight increases in the probabilities of serious injury and death. Other factors which have a similar or greater effect on the probabilities of different types of injury include seating position, blood alcohol level, vehicle type, vehicle make and type of collision.     

Exploring the overall and specific crash severity levels at signalized intersections

Many studies have shown that intersections are among the most dangerous locations of a roadway network. Therefore, there is a need to understand the factors that contribute to injuries at such locations. This paper addresses the different factors that affect crash injury severity at signalized intersections. It also looks into the quality and completeness of the crash data and the effect that incomplete data has on the final results. Data from multiple sources have been cross-checked to ensure the completeness of all crashes including minor crashes that are usually unreported or not coded into crash databases. The ordered probit modeling technique has been adopted in this study to account for the fact that injury levels are naturally ordered variables. The tree-based regression methodology has also been adopted in this study to explore the factors that affect each severity level. The probit model results showed that a combination of crash-specific information and intersection characteristics result in the highest prediction rate of injury level. More specifically, having a divided minor roadway or a higher speed limit on the minor roadway decreased the level of injury while crashes involving a pedestrian/bicyclist and left turn crashes had the highest probability of a more severe crash. Several regression tree models showed a difference in the significant factors that affect the different severity types. Completing the data with minor non injury crashes improved the modeling results and depicted differences when modeling the no injury crashes.     

Analysis of crash parameters and driver characteristics associated with lower limb injury

This study aims to investigate changes in frequency, risk, and patterns of lower limb injuries due to vehicle and occupant parameters as a function of vehicle model year. From the National Automotive Sampling System-Crashworthiness Data System, 10,988 observations were sampled and analyzed, representing 4.7 million belted drivers involved in frontal crashes for the years 1998–2010.A logistic regression model was developed to understand the association of sustaining knee and below knee lower limb injuries of moderate or greater severity with motor vehicle crash characteristics such as vehicle type and model years, toepan and instrument panel intrusions in addition to the occupant’s age, gender, height and weight. Toepan intrusion greater than 2 cm was significantly associated with an increased likelihood of injury (odds ratio: 9.10, 95% confidence interval 1.82–45.42). Females sustained a higher likelihood of distal lower limb injuries (OR: 6.83, 1.56–29.93) as compared to males. Increased mass of the driver was also found to have a positive association with injury (OR: 1.04, 1.02–1.06), while age and height were not associated with injury likelihood. Relative to passenger cars, vans exhibited a protective effect against sustaining lower limb injury (OR: 0.24, 0.07–0.78), whereas no association was shown for light trucks (OR: 1.31, 0.69–2.49) or SUVs (OR: 0.76, 0.28–2.02).To examine whether current crash testing results are representative of real-world NASS-CDS findings, data from frontal offset crash tests performed by the Insurance Institute for Highway Safety (IIHS) were examined. IIHS data indicated a decreasing trend in vehicle foot well and toepan intrusion, foot accelerations, tibia axial forces and tibia index in relation to increasing vehicle model year between the year 1995 and 2013. Over 90% of vehicles received the highest IIHS rating, with steady improvement from the upper and lower tibia index, tibia axial force and the resultant foot acceleration considering both left and right extremities. Passenger cars received the highest rating followed by SUVs and light trucks, while vans attained the lowest rating.These results demonstrate that while there has been steady improvement in vehicle crash test performance, below-knee lower extremity injuries remain the most common AIS 2+ injury in real-world frontal crashes.     

A kinetic energy model of two-vehicle crash injury severity

An important part of any model of vehicle crashes is the development of a procedure to estimate crash injury severity. After reviewing existing models of crash severity, this paper outlines the development of a modelling approach aimed at measuring the injury severity of people in two-vehicle road crashes. This model can be incorporated into a discrete event traffic simulation model, using simulation model outputs as its input. The model can then serve as an integral part of a simulation model estimating the crash potential of components of the traffic system. The model is developed using Newtonian Mechanics and Generalised Linear Regression. The factors contributing to the speed change (ΔV_s) of a subject vehicle are identified using the law of conservation of momentum. A Log-Gamma regression model is fitted to measure speed change (ΔV_s) of the subject vehicle based on the identified crash characteristics. The kinetic energy applied to the subject vehicle is calculated by the model, which in turn uses a Log-Gamma Regression Model to estimate the Injury Severity Score of the crash from the calculated kinetic energy, crash impact type, presence of airbag and/or seat belt and occupant age.     

Risk factors affecting the severity of single vehicle traffic accidents in Hong Kong

A population-based case-control study was conducted to examine factors affecting the severity of single vehicle traffic accidents in Hong Kong. In particular, single vehicle accident data of three major vehicle types, namely private vehicles, goods vehicles and motorcycles, which contributed to over 80% of all single vehicle accidents during the 2-year-period 1999-2000, were considered. Data were obtained from the newly implemented traffic accident data system (TRADS), which was developed jointly by the Transport Department, Police Force and Information Technology Services Department, Hong Kong. The effect of district, human, vehicle, safety, environmental and site factors on injury severity of an accident was examined. Unique risk factors associated with each of the vehicle types were identified by means of stepwise logistic regression models. For private vehicles, district board, gender of driver, age of vehicle, time of the accident and street light conditions are significant factors determining injury severity. For goods vehicles, seat-belt usage and weekday occurrence are the only two significant factors associated with injury severity. For motorcycles, age of vehicle, weekday and time of the accident were determined to be important factors affecting the injury severity. Identification of potential risk factors pertinent to the particular vehicle type has important implications to relevant official organisations in modifying safety measures in order to reduce the occurrence of severe traffic accidents, which would help to promote a safe road environment.     

Comparison of the binary logistic and skewed logistic (Scobit) models of injury severity in motor vehicle collisions

The binary logistic model has been extensively used to analyze traffic collision and injury data where the outcome of interest has two categories. However, the assumption of a symmetric distribution may not be a desirable property in some cases, especially when there is a significant imbalance in the two categories of outcome. This study compares the standard binary logistic model with the skewed logistic model in two cases in which the symmetry assumption is violated in one but not the other case. The differences in the estimates, and thus the marginal effects obtained, are significant when the assumption of symmetry is violated.     

Analysis of driver injury severity in wrong-way driving crashes on controlled-access highways

For more than five decades, wrong-way driving (WWD) has been notorious as a traffic safety issue for controlled-access highways. Numerous studies and efforts have tried to identify factors that contribute to WWD occurrences at these sites in order to delineate between WWD and non-WWD crashes. However, none of the studies investigate the effect of various confounding variables on the injury severity being sustained by the at-fault drivers in a WWD crash. This study tries to fill this gap in the existing literature by considering possible variables and taking into account the ordinal nature of injury severity using three different ordered-response models: ordered logit or proportional odds (PO), generalized ordered logit (GOL), and partial proportional odds (PPO) model. The findings of this study reveal that a set of variables, including driver’s age, condition (i.e., intoxication), seatbelt use, time of day, airbag deployment, type of setting, surface condition, lighting condition, and type of crash, has a significant effect on the severity of a WWD crash. Additionally, a comparison was made between the three proposed methods. The results corroborate that the PPO model outperforms the other two models in terms of modeling injury severity using our database. Based on the findings, several countermeasures at the engineering, education, and enforcement levels are recommended.     

A mixed generalized ordered response model for examining pedestrian and bicyclist injury severity level in traffic crashes

This paper proposes an econometric structure for injury severity analysis at the level of individual accidents that recognizes the ordinal nature of the categories in which injury severity are recorded, while also allowing flexibility in capturing the effects of explanatory variables on each ordinal category and allowing heterogeneity in the effects of contributing factors due to the moderating influence of unobserved factors. The model developed here, referred to as the mixed generalized ordered response logit (MGORL) model, generalizes the standard ordered response models used in the extant literature for injury severity analysis. To our knowledge, this is the first such formulation to be proposed and applied in the econometric literature in general, and in the safety analysis literature in particular.

The MGORL model is applied to examine non-motorist injury severity in accidents in the USA, using the 2004 General Estimates System (GES) database. The empirical findings emphasize the inconsistent results obtained from the standard ordered response model. An important policy result from our analysis is that the general pattern and relative magnitude of elasticity effects of injury severity determinants are similar for pedestrians and bicyclists. The analysis also suggests that the most important variables influencing non-motorist injury severity are the age of the individual (the elderly are more injury-prone), the speed limit on the roadway (higher speed limits lead to higher injury severity levels), location of crashes (those at signalized intersections are less severe than those elsewhere), and time-of-day (darker periods lead to higher injury severity).     

Analysis of injury severity of drivers involved in single- and two-vehicle crashes on highways in Ontario

This study analyzes driver's injury severity in single- and two-vehicle crashes and compares the effects of explanatory variables among various types of crashes. The study identified factors affecting injury severity and their effects on severity levels using 5-year crash records for provincial highways in Ontario, Canada. Considering heteroscedasticity in the effects of explanatory variables on injury severity, the heteroscedastic ordered logit (HOL) models were developed for single- and two-vehicle crashes separately. The results of the models show that there exists heteroscedasticity for young drivers (≤30), safety equipment and ejection in the single-vehicle crash model, and female drivers, safety equipment and head-on collision in the two-vehicle crash models. The results also show that young car drivers have opposite effects between single-car and car–car crashes, and sideswipe crashes have opposite effects between car–car and truck–truck crashes. The study demonstrates that separate HOL models for single-vehicle and different types of two-vehicle crashes can identify differential effects of factors on driver's injury severity.     

Diagnostic analysis of the logistic model for pedestrian injury severity in traffic crashes

This study attempts to evaluate the injury risk of pedestrian casualties in traffic crashes and to explore the factors that contribute to mortality and severe injury, using the comprehensive historical crash record that is maintained by the Hong Kong Transport Department. The injury, demographic, crash, environmental, geometric, and traffic characteristics of 73,746 pedestrian casualties that were involved in traffic crashes from 1991 to 2004 are considered. Binary logistic regression is used to determine the associations between the probability of fatality and severe injury and all contributory factors. A consideration of the influence of implicit attributes on the trend of pedestrian injury risk, temporal confounding, and interaction effects is progressively incorporated into the predictive model. To verify the goodness-of-fit of the proposed model, the Hosmer–Lemeshow test and logistic regression diagnostics are conducted. It is revealed that there is a decreasing trend in pedestrian injury risk, controlling for the influences of demographic, road environment, and other risk factors. In addition, the influences of pedestrian behavior, traffic congestion, and junction type on pedestrian injury risk are subject to temporal variation.     

Analysis of traffic accident injury severity on Spanish rural highways using Bayesian networks

Several different factors contribute to injury severity in traffic accidents, such as driver characteristics, highway characteristics, vehicle characteristics, accidents characteristics, and atmospheric factors. This paper shows the possibility of using Bayesian Networks (BNs) to classify traffic accidents according to their injury severity. BNs are capable of making predictions without the need for pre assumptions and are used to make graphic representations of complex systems with interrelated components. This paper presents an analysis of 1536 accidents on rural highways in Spain, where 18 variables representing the aforementioned contributing factors were used to build 3 different BNs that classified the severity of accidents into slightly injured and killed or severely injured. The variables that best identify the factors that are associated with a killed or seriously injured accident (accident type, driver age, lighting and number of injuries) were identified by inference.     

Comparison of reporting of seat belt use by police and crash investigators: variation in agreement by injury severity

Purpose: To evaluate agreement between police and trained investigators regarding seat belt use by crash victims, according to injury severity. Methods: We used data from the National Accident Sampling System Crashworthiness Data System (CDS) for front seat occupants, 16 years and older, in crashes during 1993–2000. Crashworthiness Data System investigators determined belt use from vehicle inspection, interviews, and medical record information; their assessment was considered the gold standard for this analysis. Occupant severity of injury was categorized in five levels from no injuries to death. We estimated the sensitivity, specificity, and area under receiver operating characteristic curves for police reports of belt use. Results: Among 48,858 occupants, sensitivity of a police report that a belt was used was 95.8% overall and varied only modestly by injury severity. Specificity of a police report that a belt was not used was 69.1% overall; it was the lowest among the uninjured (53.2%) and greatest among the dead (90.4%). The area under the curve was 0.82 (95% confidence interval 0.82–0.83) overall; this was lowest among those not injured (0.75, 95% confidence interval 0.74–0.76) and increased with injury severity to 0.91 (95% confidence interval 0.90–0.93) among those who died. Conclusion: Police usually classify belted crash victims as belted, regardless of injury severity. But they often classify unbelted survivors as belted when they were not. This misclassification may result in exaggerated estimates of seat belt effectiveness in some studies.     

Analysis of traffic injury severity: an application of non-parametric classification tree techniques

Statistical regression models, such as logit or ordered probit/logit models, have been widely employed to analyze injury severity of traffic accidents. However, most regression models have their own model assumptions and pre-defined underlying relationships between dependent and independent variables. If these assumptions are violated, the model could lead to erroneous estimations of injury likelihood. The classification and regression tree (CART), one of the most widely applied data mining techniques, has been commonly employed in business administration, industry, and engineering. CART does not require any pre-defined underlying relationship between target (dependent) variable and predictors (independent variables) and has been shown to be a powerful tool, particularly for dealing with prediction and classification problems. This study uses the 2001 accident data for Taipei, Taiwan. A CART model was developed to establish the relationship between injury severity and driver/vehicle characteristics, highway/environmental variables and accident variables. The results indicate that the most important variable associated with crash severity is the vehicle type. Pedestrians, motorcycle and bicycle riders are identified to have higher risks of being injured than other types of vehicle drivers in traffic accidents.     

Exploring the effects of roadway characteristics on the frequency and severity of head-on crashes: Case studies from Malaysian Federal Roads

Head-on crashes are among the most severe collision types and of great concern to road safety authorities. Therefore, it justifies more efforts to reduce both the frequency and severity of this collision type. To this end, it is necessary to first identify factors associating with the crash occurrence. This can be done by developing crash prediction models that relate crash outcomes to a set of contributing factors. This study intends to identify the factors affecting both the frequency and severity of head-on crashes that occurred on 448 segments of five federal roads in Malaysia. Data on road characteristics and crash history were collected on the study segments during a 4-year period between 2007 and 2010. The frequency of head-on crashes were fitted by developing and comparing seven count-data models including Poisson, standard negative binomial (NB), random-effect negative binomial, hurdle Poisson, hurdle negative binomial, zero-inflated Poisson, and zero-inflated negative binomial models. To model crash severity, a random-effect generalized ordered probit model (REGOPM) was used given a head-on crash had occurred. With respect to the crash frequency, the random-effect negative binomial (RENB) model was found to outperform the other models according to goodness of fit measures. Based on the results of the model, the variables horizontal curvature, terrain type, heavy-vehicle traffic, and access points were found to be positively related to the frequency of head-on crashes, while posted speed limit and shoulder width decreased the crash frequency. With regard to the crash severity, the results of REGOPM showed that horizontal curvature, paved shoulder width, terrain type, and side friction were associated with more severe crashes, whereas land use, access points, and presence of median reduced the probability of severe crashes. Based on the results of this study, some potential countermeasures were proposed to minimize the risk of head-on crashes.     

Underreporting in traffic accident data, bias in parameters and the structure of injury severity models

Injury severities in traffic accidents are usually recorded on ordinal scales, and statistical models have been applied to investigate the effects of driver factors, vehicle characteristics, road geometrics and environmental conditions on injury severity. The unknown parameters in the models are in general estimated assuming random sampling from the population. Traffic accident data however suffer from underreporting effects, especially for lower injury severities. As a result, traffic accident data can be regarded as outcome-based samples with unknown population shares of the injury severities. An outcome-based sample is overrepresented by accidents of higher severities. As a result, outcome-based samples result in biased parameters which skew our inferences on the effect of key safety variables such as safety belt usage. The pseudo-likelihood function for the case with unknown population shares, which is the same as the conditional maximum likelihood for the case with known population shares, is applied in this study to examine the effects of severity underreporting on the parameter estimates. Sequential binary probit models and ordered-response probit models of injury severity are developed and compared in this study. Sequential binary probit models assume that the factors determining the severity change according to the level of the severity itself, while ordered-response probit models assume that the same factors correlate across all levels of severity. Estimation results suggest that the sequential binary probit models outperform the ordered-response probit models, and that the coefficient estimates for lap and shoulder belt use are biased if underreporting is not considered. Mean parameter bias due to underreporting can be significant. The findings show that underreporting on the outcome dimension may induce bias in inferences on a variety of factors. In particular, if underreporting is not accounted for, the marginal impacts of a variety of factors appear to be overestimated. Fixed objects and environmental conditions are overestimated in their impact on injury severity, as is the effect of separate lap and shoulder belt use. Combined lap and shoulder belt usage appears to be unaffected. The parameter bias is most pronounced when underreporting of possible injury accidents in addition to property damage only accidents is taken into account.