Highway accident severities and the mixed logit model: an exploratory empirical analysis

Many transportation agencies use accident frequencies, and statistical models of accidents frequencies, as a basis for prioritizing highway safety improvements. However, the use of accident severities in safety programming has been often been limited to the locational assessment of accident fatalities, with little or no emphasis being placed on the full severity distribution of accidents (property damage only, possible injury, injury)-which is needed to fully assess the benefits of competing safety-improvement projects. In this paper we demonstrate a modeling approach that can be used to better understand the injury-severity distributions of accidents on highway segments, and the effect that traffic, highway and weather characteristics have on these distributions. The approach we use allows for the possibility that estimated model parameters can vary randomly across roadway segments to account for unobserved effects potentially relating to roadway characteristics, environmental factors, and driver behavior. Using highway-injury data from Washington State, a mixed (random parameters) logit model is estimated. Estimation findings indicate that volume-related variables such as average daily traffic per lane, average daily truck traffic, truck percentage, interchanges per mile and weather effects such as snowfall are best modeled as random-parameters-while roadway characteristics such as the number of horizontal curves, number of grade breaks per mile and pavement friction are best modeled as fixed parameters. Our results show that the mixed logit model has considerable promise as a methodological tool in highway safety programming.     

Modeling accident frequencies as zero-altered probability processes: An empirical inquiry

This paper presents an empirical inquiry into the applicability of zero-altered counting processes to roadway section accident frequencies. The intent of such a counting process is to distinguish sections of roadway that are truly safe (near zero-accident likelihood) from those that are unsafe but happen to have zero accidents observed during the period of observation (e.g. one year). Traditional applications of Poisson and negative binomial accident frequency models do not account for this distinction and thus can produce biased coefficient estimates because of the preponderance of zero-accident observations. Zero-altered probability processes such as the zero-inflated Poisson (ZIP) and zero-inflated negative binomial (ZINB) distributions are examined and proposed for accident frequencies by roadway functional class and geographic location. The findings show that the ZIP structure models are promising and have great flexibility in uncovering processes affecting accident frequencies on roadway sections observed with zero accidents and those with observed accident occurrences. This flexibility allows highway engineers to better isolate design factors that contribute to accident occurrence and also provides additional insight into variables that determine the relative accident likelihoods of safe versus unsafe roadways. The generic nature of the models and the relatively good power of the Vuong specification test used in the non-nested hypotheses of model specifications offers roadway designers the potential to develop a global family of models for accident frequency prediction that can be embedded in a larger safety management system.     

The effect of ice warning signs on ice-accident frequencies and severities

Signing of non-permanent road surface conditions, such as ice, is difficult because hazard formation, location, and duration are unpredictable. Subsequently, many state transportation departments have begun to question the sensibility of expending material and personnel resources to maintain ice warning signs when little proof exists of their effectiveness in improving highway safety. This research statistically studies the effectiveness of ice warning signs in reducing accident frequency and accident severity in Washington State. Our findings show that the presence of ice warning signs was not a significant factor in reducing ice-accident frequency or ice-accident severity. However, we were able to identify significant spatial, temporal, traffic, roadway and accident characteristics that influenced ice-accident frequency and severity. The identification of these characteristics will allow for better placement of ice warning signs and improvements in roadway and roadside design that can reduce the frequency and severity of ice-related accidents.     

Analyzing the severity of accidents on the German Autobahn

We study the severity of accidents on the German Autobahn in the state of North Rhine-Westphalia using data for the years 2009 until 2011. We use a multinomial logit model to identify statistically relevant factors explaining the severity of the most severe injury, which is classified into the four classes fatal, severe injury, light injury and property damage. Furthermore, to account for unobserved heterogeneity we use a random parameter model. We study the effect of a number of factors including traffic information, road conditions, type of accidents, speed limits, presence of intelligent traffic control systems, age and gender of the driver and location of the accident. Our findings are in line with studies in different settings and indicate that accidents during daylight and at interchanges or construction sites are less severe in general. Accidents caused by the collision with roadside objects, involving pedestrians and motorcycles, or caused by bad sight conditions tend to be more severe. We discuss the measures of the 2011 German traffic safety programm in the light of our results.     

A study of factors affecting highway accident rates using the random-parameters tobit model

A large body of previous literature has used a variety of count-data modeling techniques to study factors that affect the frequency of highway accidents over some time period on roadway segments of a specified length. An alternative approach to this problem views vehicle accident rates (accidents per mile driven) directly instead of their frequencies. Viewing the problem as continuous data instead of count data creates a problem in that roadway segments that do not have any observed accidents over the identified time period create continuous data that are left-censored at zero. Past research has appropriately applied a tobit regression model to address this censoring problem, but this research has been limited in accounting for unobserved heterogeneity because it has been assumed that the parameter estimates are fixed over roadway-segment observations. Using 9-year data from urban interstates in Indiana, this paper employs a random-parameters tobit regression to account for unobserved heterogeneity in the study of motor-vehicle accident rates. The empirical results show that the random-parameters tobit model outperforms its fixed-parameters counterpart and has the potential to provide a fuller understanding of the factors determining accident rates on specific roadway segments.     

Markov switching multinomial logit model: An application to accident-injury severities

In this study, two-state Markov switching multinomial logit models are proposed for statistical modeling of accident-injury severities. These models assume Markov switching over time between two unobserved states of roadway safety as a means of accounting for potential unobserved heterogeneity. The states are distinct in the sense that in different states accident-severity outcomes are generated by separate multinomial logit processes. To demonstrate the applicability of the approach, two-state Markov switching multinomial logit models are estimated for severity outcomes of accidents occurring on Indiana roads over a four-year time period. Bayesian inference methods and Markov Chain Monte Carlo (MCMC) simulations are used for model estimation. The estimated Markov switching models result in a superior statistical fit relative to the standard (single-state) multinomial logit models for a number of roadway classes and accident types. It is found that the more frequent state of roadway safety is correlated with better weather conditions and that the less frequent state is correlated with adverse weather conditions.     

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.     

Landscaping of highway medians and roadway safety at unsignalized intersections

Well-planted and maintained landscaping can help reduce driving stress, provide better visual quality, and decrease over speeding, thus improving roadway safety. Florida Department of Transportation (FDOT) Standard Index (SI-546) is one of the more demanding standards in the U.S. for landscaping design criteria at highway medians near intersections. The purposes of this study were to (1) empirically evaluate the safety results of SI-546 at unsignalized intersections and (2) quantify the impacts of geometrics, traffic, and landscaping design features on total crashes and injury plus fatal crashes. The studied unsignalized intersections were divided into (1) those without median trees near intersections, (2) those with median trees near intersections that were compliant with SI-546, and (3) those with median trees near intersections that were non-compliant with SI-546. A total of 72 intersections were selected, for which five-year crash data from 2006–2010 were collected.The sites that were compliant with SI-546 showed the best safety performance in terms of the lowest crash counts and crash rates. Four crash predictive models—two for total crashes and two for injury crashes—were developed. The results indicated that improperly planted and maintained median trees near highway intersections can increase the total number of crashes and injury plus fatal crashes at a 90% confidence level; no significant difference could be found in crash rates between sites that were compliant with SI-546 and sites without trees. All other conditions remaining the same, an intersection with trees that was not compliant with SI-546 had 63% more crashes and almost doubled injury plus fatal crashes than those at intersections without trees. The study indicates that appropriate landscaping in highway medians near intersections can be an engineering technology that not only improves roadway environmental quality but also maintains intersection safety.     

Using logistic regression to estimate the influence of accident factors on accident severity

Logistic regression was applied to accident-related data collected from traffic police records in order to examine the contribution of several variables to accident severity. A total of 560 subjects involved in serious accidents were sampled. Accident severity (the dependent variable) in this study is a dichotomous variable with two categories, fatal and non-fatal. Therefore, each of the subjects sampled was classified as being in either a fatal or non-fatal accident. Because of the binary nature of this dependent variable, a logistic regression approach was found suitable. Of nine independent variables obtained from police accident reports, two were found most significantly associated with accident severity, namely, location and cause of accident. A statistical interpretation is given of the model-developed estimates in terms of the odds ratio concept. The findings show that logistic regression as used in this research is a promising tool in providing meaningful interpretations that can be used for future safety improvements in Riyadh.     

Injury severities of truck drivers in single- and multi-vehicle accidents on rural highways

In adverse driving conditions, such as inclement weather and/or complex terrain, trucks are often involved in single-vehicle (SV) accidents in addition to multi-vehicle (MV) accidents. Ten-year accident data involving trucks on rural highway from the Highway Safety Information System (HSIS) is studied to investigate the difference in driver-injury severity between SV and MV accidents by using mixed logit models. Injury severity from SV and MV accidents involving trucks on rural highways is modeled separately and their respective critical risk factors such as driver, vehicle, temporal, roadway, environmental and accident characteristics are evaluated. It is found that there exists substantial difference between the impacts from a variety of variables on the driver-injury severity in MV and SV accidents. By conducting the injury severity study for MV and SV accidents involving trucks separately, some new or more comprehensive observations, which have not been covered in the existing studies can be made. Estimation findings indicate that the snow road surface and light traffic indicators will be better modeled as random parameters in SV and MV models respectively. As a result, the complex interactions of various variables and the nature of truck-driver injury are able to be disclosed in a better way. Based on the improved understanding on the injury severity of truck drivers from truck-involved accidents, it is expected that more rational and effective injury prevention strategy may be developed for truck drivers under different driving conditions in the future.     

Impact of roadside features on the frequency and severity of run-off-roadway accidents: an empirical analysis

In the US, single-vehicle run-off-roadway accidents result in a million highway crashes with roadside features every year and account for approximately one third of all highway fatalities. Despite the number and severity of run-off-roadway accidents, quantification of the effect of possible countermeasures has been surprisingly limited due to the absence of data (particularly data on roadside features) needed to rigorously analyze factors affecting the frequency and severity of run-off-roadway accidents. This study provides some initial insight into this important problem by combining a number of databases, including a detailed database on roadside features, to analyze run-off-roadway accidents on a 96.6-km section of highway in Washington State. Using zero-inflated count models and nested logit models, statistical models of accident frequency and severity are estimated and the findings isolate a wide range of factors that significantly influence the frequency and severity of run-off-roadway accidents. The marginal effects of these factors are computed to provide an indication on the effectiveness of potential countermeasures. The findings show significant promise in applying new methodological approaches to run-off-roadway accident analysis.     

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.     

Analyzing fault and severity in pedestrian–motor vehicle accidents in China

The number of pedestrian–motor vehicle accidents and pedestrian deaths in China surged in recent years. However, a large scale empirical research on pedestrian traffic crashes in China is lacking. In this study, we identify significant risk factors associated with fault and severity in pedestrian–motor vehicle accidents. Risk factors in several different dimensions, including pedestrian, driver, vehicle, road and environmental factors, are considered. We analyze 6967 pedestrian traffic accident reports for the period 2006–2010 in Guangdong Province, China. These data, obtained from the Guangdong Provincial Security Department, are extracted from the Traffic Management Sector-Specific Incident Case Data Report. Pedestrian traffic crashes have a unique inevitability and particular high risk, due to pedestrians’ fragility, slow movement and lack of lighting equipment. The empirical analysis of the present study has the following policy implications. First, traffic crashes in which pedestrians are at fault are more likely to cause serious injuries or death, suggesting that relevant agencies should pay attention to measures that prevent pedestrians from violating traffic rules. Second, both the attention to elderly pedestrians, male and experienced drivers, the penalty to drunk driving, speeding, driving without a driver's license and other violation behaviors should be strengthened. Third, vehicle safety inspections and safety training sessions for truck drivers should be reinforced. Fourth, improving the road conditions and road lighting at night are important measures in reducing the probability of accident casualties. Fifth, specific road safety campaigns in rural areas, and education programs especially for young children and teens should be developed and promoted. Moreover, we reveal a country-specific factor, hukou, which has significant effect on the severity in pedestrian accidents due to the discrepancy in the level of social insurance/security, suggesting that equal social security level among urban and rural people should be set up. In addition, establishing a comprehensive liability distribution system for non-urban areas and roadways will be conducive to both pedestrians’ and drivers’ voluntary compliance with traffic rules.     

A latent class modeling approach for identifying vehicle driver injury severity factors at highway-railway crossings

In this paper, we aim to identify the different factors that influence injury severity of highway vehicle occupants, in particular drivers, involved in a vehicle-train collision at highway-railway grade crossings. The commonly used approach to modeling vehicle occupant injury severity is the traditional ordered response model that assumes the effect of various exogenous factors on injury severity to be constant across all accidents. The current research effort attempts to address this issue by applying an innovative latent segmentation based ordered logit model to evaluate the effects of various factors on the injury severity of vehicle drivers. In this model, the highway-railway crossings are assigned probabilistically to different segments based on their attributes with a separate injury severity component for each segment. The validity and strength of the formulated collision consequence model is tested using the US Federal Railroad Administration database which includes inventory data of all the railroad crossings in the US and collision data at these highway railway crossings from 1997 to 2006. The model estimation results clearly highlight the existence of risk segmentation within the affected grade crossing population by the presence of active warning devices, presence of permanent structure near the crossing and roadway type. The key factors influencing injury severity include driver age, time of the accident, presence of snow and/or rain, vehicle role in the crash and motorist action prior to the crash.     

Evaluation of e-bike accidents in Switzerland

Background

The acceptance and usage of electric bicycles has rapidly increased in Switzerland in the last years. Hence this topic has been addressed by policy makers with the aim to facilitate new transport modes and, moreover, to improve their safety.

Methods

Police-recorded accidents of the years 2011 and 2012 involving a total of 504 e-bikers and 871 bicyclists were analysed. National figures were compared with those of a rural and an urban environment.

Results

Most e-bikers who were involved in accidents were 40–65 years old. It was found that most e-bikers sustained single accidents and that helmet usage was higher in the investigated rural environment than in the investigated urban area. The evaluation of the injury severity of e-bikers, particularly compared to bicyclists, lead to diverging results.

Conclusions

The findings presented in this study are intended to serve as a benchmark since basic information on characteristics of e-bike accidents is provided. With respect to differences between the injury severity of e-bikers and bicyclists to-date no clear statement can be drawn. It is suggested to regularly evaluate e-bike accidents to show trends and/or identify changes.     

The statistical analysis of highway crash-injury severities: a review and assessment of methodological alternatives

Reducing the severity of injuries resulting from motor-vehicle crashes has long been a primary emphasis of highway agencies and motor-vehicle manufacturers. While progress can be simply measured by the reduction in injury levels over time, insights into the effectiveness of injury-reduction technologies, policies, and regulations require a more detailed empirical assessment of the complex interactions that vehicle, roadway, and human factors have on resulting crash-injury severities. Over the years, researchers have used a wide range of methodological tools to assess the impact of such factors on disaggregate-level injury-severity data, and recent methodological advances have enabled the development of sophisticated models capable of more precisely determining the influence of these factors. This paper summarizes the evolution of research and current thinking as it relates to the statistical analysis of motor-vehicle injury severities, and provides a discussion of future methodological directions.     

A multivariate Poisson-lognormal regression model for prediction of crash counts by severity, using Bayesian methods

Numerous efforts have been devoted to investigating crash occurrence as related to roadway design features, environmental factors and traffic conditions. However, most of the research has relied on univariate count models; that is, traffic crash counts at different levels of severity are estimated separately, which may neglect shared information in unobserved error terms, reduce efficiency in parameter estimates, and lead to potential biases in sample databases. This paper offers a multivariate Poisson-lognormal (MVPLN) specification that simultaneously models crash counts by injury severity. The MVPLN specification allows for a more general correlation structure as well as overdispersion. This approach addresses several questions that are difficult to answer when estimating crash counts separately. Thanks to recent advances in crash modeling and Bayesian statistics, parameter estimation is done within the Bayesian paradigm, using a Gibbs Sampler and the Metropolis–Hastings (M–H) algorithms for crashes on Washington State rural two-lane highways. Estimation results from the MVPLN approach show statistically significant correlations between crash counts at different levels of injury severity. The non-zero diagonal elements suggest overdispersion in crash counts at all levels of severity. The results lend themselves to several recommendations for highway safety treatments and design policies. For example, wide lanes and shoulders are key for reducing crash frequencies, as are longer vertical curves.     

Willingness to use safety belt and levels of injury in car accidents

In this article, we develop a bivariate ordered Probit model to analyze the decision to fasten the safety belt in a car and the resulting severity of accidents if it happens. The approach takes into account the fact that the decision to fasten the safety belt has a direct causal effect on the category of injury if an accident happens. Our application to a sample drawn from the database of French accident reports in 2003 for three populations of car users (drivers, front passengers, rear passengers) shows that fastening the safety belt is significantly related to a decrease in severe injuries but it shows also that these car users compensate partly for this safety benefit. Furthermore, it is observed that demographic characteristics of car users, as well as transport facilities, play important roles in decisions to fasten safety belts and in the eventual resulting accident injuries.     

The impact of traffic violations on the estimated cost of traffic accidents with victims

We analyse accidents with victims and calculate the influence of traffic violations on the probability of having a serious or fatal accident, compared to a slight accident. Traffic violations related to speed limitations, administrative infringements or faults related to the driver are considered. Data were obtained from all available reports on accidents with victims that occurred in Spain from 2003 to 2005. A multinomial logistic regression model is specified to find the probability that an accident with victims is slight, serious or fatal, given the presence/absence of thirty different types of traffic violations. The average cost per victim and the average number of victims per accident are then used to find the estimated cost of an accident with victims, given the information on the traffic violations incurred. This demonstrates which combinations of traffic violations lead to higher estimated average costs, compared to cases in which no traffic violation occurred. We conclude with some recommendations on the severity of penalties, and suggest that regulators penalize the occurrences of some specific combinations of traffic violations more rigorously.     

Bayesian ranking of sites for engineering safety improvements: decision parameter, treatability concept, statistical criterion, and spatial dependence

In recent years, there has been a renewed interest in applying statistical ranking criteria to identify sites on a road network, which potentially present high traffic crash risks or are over-represented in certain type of crashes, for further engineering evaluation and safety improvement. This requires that good estimates of ranks of crash risks be obtained at individual intersections or road segments, or some analysis zones. The nature of this site ranking problem in roadway safety is related to two well-established statistical problems known as the small area (or domain) estimation problem and the disease mapping problem. The former arises in the context of providing estimates using sample survey data for a small geographical area or a small socio-demographic group in a large area, while the latter stems from estimating rare disease incidences for typically small geographical areas. The statistical problem is such that direct estimates of certain parameters associated with a site (or a group of sites) with adequate precision cannot be produced, due to a small available sample size, the rareness of the event of interest, and/or a small exposed population or sub-population in question. Model based approaches have offered several advantages to these estimation problems, including increased precision by "borrowing strengths" across the various sites based on available auxiliary variables, including their relative locations in space. Within the model based approach, generalized linear mixed models (GLMM) have played key roles in addressing these problems for many years. The objective of the study, on which this paper is based, was to explore some of the issues raised in recent roadway safety studies regarding ranking methodologies in light of the recent statistical development in space-time GLMM. First, general ranking approaches are reviewed, which include na?ve or raw crash-risk ranking, scan based ranking, and model based ranking. Through simulations, the limitation of using the na?ve approach in ranking is illustrated. Second, following the model based approach, the choice of decision parameters and consideration of treatability are discussed. Third, several statistical ranking criteria that have been used in biomedical, health, and other scientific studies are presented from a Bayesian perspective. Their applications in roadway safety are then demonstrated using two data sets: one for individual urban intersections and one for rural two-lane roads at the county level. As part of the demonstration, it is shown how multivariate spatial GLMM can be used to model traffic crashes of several injury severity types simultaneously and how the model can be used within a Bayesian framework to rank sites by crash cost per vehicle-mile traveled (instead of by crash frequency rate). Finally, the significant impact of spatial effects on the overall model goodness-of-fit and site ranking performances are discussed for the two data sets examined. The paper is concluded with a discussion on possible directions in which the study can be extended.