Examining the performance of engineering treatment evaluation methodologies using the hypothetical treatment and actual treatment settings.

The selection of treatment evaluation methodology is paramount in determining reliable crash modification factors (CMFs) for engineering treatments. A lack of ground truth makes it cumbersome to examine the performance of treatment evaluation methodologies. In addition, a sound methodological framework is critical for evaluating the performances of treatment evaluation methodologies. In addressing these challenges, this study proposed a framework for assessing treatment evaluation methodologies by hypothetical treatments with known ground truth and actual real-world treatments. In particular, this study examined three before-after treatment evaluation approaches: 1) Empirical Bayes, 2) Simulation-based Empirical Bayes, and 3) Full Bayes methods. In addition, this study examined the Cross-Sectional treatment evaluation methodology. The methodological framework utilized five datasets of hypothetical treatment with known ground truth based on the hotspot identification method and a real-world dataset of wide centerline treatment on two-lane, two-way rural highways in Queensland, Australia. Results showed that all the methods could identify the ground truth of hypothetical treatments, but the Full Bayes approach better predicts the known ground truth compared to Empirical Bayes, Simulation-based Empirical Bayes, and Cross-Sectional methods. The Full Bayes approach was also found to provide the most precise estimate for real-world wide centerline treatment along rural highways compared to other methods. Moreover, the current study highlighted that the Cross-Sectional method offers a viable estimate of treatment effectiveness in case the before-period data is limited.

Effects of design consistency on run-off-road crashes: An application of a Random Parameters Negative Binomial Lindley model.

Run-off-road crashes are one of the most common crash types, especially in rural roadway environments contributing significantly to fatalities and severe injuries. These crashes are complex and multi-dimensional events, and factors like road geometry, driver behaviour, traffic characteristics and roadside features contribute to their occurrence, separately or interactively. Sudden changes in road geometry, in particular, can influence driver behaviour, and therefore, in developing a micro-level crash risk model for run-off-road crashes, one of the challenges is incorporating the effects of driver behaviour (disaggregated information) that may arise from the variations in road geometry (aggregated information). This study aims to examine the interaction between road geometry and driver behaviour through a set of measures for design consistency on two-lane rural roads. Multiple data sources, including crash data for 2014-18, traffic data, probe speed data and roadway geometric data, for twenty-three highways in Queensland, Australia, have been fused for this study. Seventeen types of design consistency measures with regard to alignment consistency, operating speed consistency and driving dynamics are tested. A run-off-road crash risk model is estimated by employing the Random Parameters Negative Binomial Lindley regression framework, which accounts for excess zeros in the crash counts and captures the effects of unobserved heterogeneity in the parameter estimates. Results indicate that the geometric design consistency capturing the interaction between driver behaviour and operational factors better predicts run-off-road crashes along rural highways. In addition, roadside attributes like clear zone width, infrastructures, terrain, and roadway remoteness also contribute to run-off-road crashes. The findings of the study provide a comprehensive understanding of the influence of variations in roadway geometry on driver behaviour and run-off-road crashes along rural highways.

A before-after evaluation of protected right-turn signal phasings by applying Empirical Bayes and Full Bayes approaches with heterogenous count data models.

Right-turn crashes (or left-turn crashes for the US or similar countries) represent over 40 % of signalized intersection crashes in Queensland, Australia. Protected right-turn phasings are a widely used countermeasure for right-turn crashes, but the research findings on their effects across different crash types and intersection types are not consistent. Methodologically, the Empirical Bayes and Full Bayes techniques are generally applied for before-after evaluations, but the inclusion of heterogeneous models within these techniques has not been considered much. Addressing these research gaps, the objective of this study is to evaluate the effectiveness of protected right-turn signal phasings at signalized intersections employing heterogeneous count data models with the Empirical Bayes and Full Bayes techniques. In particular, the Empirical Bayes approach based on random parameters Poisson-Gamma models (simulation-based Empirical Bayes), and the Full Bayes approach based on random parameters Poisson-Lognormal intervention models (simulation-based Full Bayes) are applied. A total of 69 Cross intersections (with ten treated sites) and 47 T intersections (with six treated sites) from Southeast Queensland in Australia were included in the analysis to estimate the effects of protected right-turn signal phasings on various crash types. Results show that the change of signal phasing from a permissive right-turn phasing to the protected right-turn phasing at cross and T intersections reduces about 87 % and 91 % of right-turn crashes, respectively. In addition, the effect of protected right-turn phasings on rear-end crashes was not significant. The heterogenous count data models significantly address extra Poisson variation, leading to efficient safety estimates in both simulation-based Empirical Bayes and simulation-based Full Bayes approaches. This study demonstrates the importance of accounting for unobserved heterogeneity for the before-after evaluation of engineering countermeasures.

Crash severity analysis and risk factors identification based on an alternate data source: a case study of developing country.

Road traffic injuries are one of the primary reasons for death, especially in developing countries like Bangladesh. Safety in land transport is one of the major concerns for road safety authorities and other policymakers. For this reason, contributory factors identification associated with crashes is necessary for reducing road crashes and ensuring transportation safety. This paper presents an analytical approach to identifying significant contributing factors of Bangladesh road crashes by evaluating the road crash data, considering three different severity levels (non-fetal, severe, and extremely severe). Generally, official crash databases are compiled from police-reported crash records. Though the official datasets are focusing on compiling a wide array of attributes, an assorted number of unreported issues can be observed that demands an alternative source of crash data. Therefore, this proposed approach considers compiling crash data from newspapers in Bangladesh which could be complimentary to the official crash database. To conduct the analysis, first, we filtered the useful features from compiled crash data using three popular feature selection techniques: chi-square, Two-way ANOVA, and Regression analysis. Then, we employed three machine learning classifiers: Decision Tree, Random Forest, and Naïve Bayes over the extracted features. A confusion matrix was considered to evaluate the proposed model, including classification accuracy, sensitivity, and specificity. The predictive machine learning model, namely, Random Forest using Label Encoder with chi-square and Two-way ANOVA feature selection process, seems the best option for crash severity prediction that provides high prediction accuracy. The resulting model highlights nine out of fourteen independent features as responsible factors. Significant features associated with crash severities include driver characteristics (gender, license type, seat belts), vehicle characteristics (vehicle type), road characteristics (road surface type, road classification), environmental conditions (day of crash occurred, time of crash), and injury localization. This outcome may contribute to improving traffic safety of Bangladesh.

Influence of segmentation approaches on the before-after evaluation of engineering treatments: A hypothetical treatment approach.

The segmentation of highways is a fundamental step in estimating crash frequency models and conducting a before-after evaluation of engineering treatments, but the effects of segmentation approaches on the engineering treatment evaluations are not known very well. This study examined the effects of segmentation approaches on the before-after evaluation of engineering treatments. In particular, this study evaluated four segmentation approaches by applying the Empirical Bayes technique to a dataset for which the ground truth was known. Four segmentation approaches included Highway Safety Manual (HSM), Fixed (kilometre post), Fisher's, and K-means segmentation. This study utilized a 440 km stretch of rural two-lane two-way highway in Queensland, Australia, to prepare a dataset with known ground truth. The treatment under evaluation was a hypothetical treatment, which should yield a crash modification factor (CMF) of 1. For assigning hypothetical treatment, a total of fifteen datasets were prepared, including ten datasets based on the random assignment and five datasets based on the hotspot identification method. Following the before-after evaluation using the Empirical Bayes technique, the results showed that HSM and Fixed segmentation approaches predict the ground truth in both dataset types. From random assignment datasets, the estimated CMFs using HSM, Fixed, Fisher's, and K-means segmentation approaches deviated from the true CMF (i.e., 1) by 2.32 %, 5.30 %, 6.08 %, and 8.62 %, respectively. In the case of hotspots, the corresponding deviations of CMFs were 8.57 %, 9.37 %, 28.84 %, and 35.43 %, respectively. Overall, HSM segmentation best identified the actual treatment effect, followed by the Fixed segmentation. If the variables to define homogeneity for HSM segmentation are limited, then Fixed segmentation can yield reliable crash modification factors from the before-after treatment evaluations than the crash-based segmentation approaches.

A simulation-based empirical bayes approach: Incorporating unobserved heterogeneity in the before-after evaluation of engineering treatments.

The Empirical Bayes approach for before-after evaluation methodology utilizing the negative binomial model does not account well for unobserved heterogeneity. Building on the Empirical Bayes approach, the objective of this study was to propose a framework to accommodate unobserved heterogeneity in before-after countermeasure evaluation. In particular, this study has proposed a simulation-based Empirical Bayes approach by applying the panel random parameters negative binomial model with parameterized overdispersion (PRNB-PO) to evaluate the effectiveness of engineering treatments. The proposed framework has been tested for the wide centerline treatment (WCLT) on rural two-lane two-way highways in Australia. The empirical analysis included 511 km of WCLT treated highways in a before-after evaluation within a time period of 2010 - 2018 and 430 km of reference sites in Queensland, Australia. The PRNB-PO models outperformed the traditional negative binomial models in terms of goodness-of-fit and prediction performance for total injury crashes, and fatal and serious injury (FSI) crashes. The simulation-based Empirical Bayes approach using the PRNB-PO model resulted in more precise estimates of crash modification factors than the standard Empirical Bayes approach. The WCLT is found to result in significant reductions in total injury crashes by 28.21% (95% confidence interval (CI) = 22.92 - 33.50%), FSI crashes by 13.90% (95% CI = 6.99 - 20.81%), and head-on crashes by 25.45% (95% CI = 14.87 - 36.03%). Overall, WCLT is an effective engineering treatment and should be considered a low-cost countermeasure on rural two-lane two-way highways.

Crash severity analysis of vulnerable road users using machine learning.

Road crash fatality is a universal problem of the transportation system. A massive death toll caused annually due to road crash incidents, and among them, vulnerable road users (VRU) are endangered with high crash severity. This paper focuses on employing machine learning-based classification approaches for modelling injury severity of vulnerable road users-pedestrian, bicyclist, and motorcyclist. Specifically, this study aims to analyse critical features associated with different VRU groups-for pedestrian, bicyclist, motorcyclist and all VRU groups together. The critical factor of crash severity outcomes for these VRU groups is estimated in identifying the similarities and differences across different important features associated with different VRU groups. The crash data for the study is sourced from the state of Queensland in Australia for the years 2013 through 2019. The supervised machine learning algorithms considered for the empirical analysis includes the K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Random Forest (RF). In these models, 17 distinct road crash parameters are considered as input features to train models, which originate from road user characteristics, weather and environment, vehicle and driver condition, period, road characteristics and regions, traffic, and speed jurisdiction. These classification models are separately trained and tested for individual and unified VRU to assess crash severity levels. Afterwards, model performances are compared with each other to justify the best classifier where Random Forest classification models for all VRU modes are found to be comparatively robust in test accuracy: (motorcyclist: 72.30%, bicyclist: 64.45%, pedestrian: 67.23%, unified VRU: 68.57%). Based on the Random Forest model, the road crash features are ranked and compared according to their impact on crash severity classification. Furthermore, a model-based partial dependency of each road crash parameters on the severity levels is plotted and compared for each individual and unified VRU. This clarifies the tendency of road crash parameters to vary with different VRU crash severity. Based on the outcome of the comparative analysis, motorcyclists are found to be more likely exposed to higher crash severity, followed by pedestrians and bicyclists.

Enhancing non-motorist safety by simulating trip exposure using a transportation planning approach.

Traditionally, in developing non-motorized crash prediction models, safety researchers have employed land use and urban form variables as surrogate for exposure information (such as pedestrian, bicyclist volumes and vehicular traffic). The quality of these crash prediction models is affected by the lack of "true" non-motorized exposure data. High-resolution modeling frameworks such as activity-based or trip-based approach could be pursued for evaluating planning level non-motorist demand. However, running a travel demand model system to generate demand inputs for non-motorized safety is cumbersome and resource intensive. The current study is focused on addressing this drawback by developing an integrated non-motorized demand and crash prediction framework for mobility and safety analysis. Towards this end, we propose a three-step framework to evaluate non-motorists safety: (1) develop aggregate level models for non-motorist generation and attraction at a zonal level, (2) develop non-motorists trip exposure matrices for safety evaluation and (3) develop aggregate level non-motorists crash frequency and severity proportion models. The framework is developed for the Central Florida region using non-motorist demand data from National Household Travel Survey (2009) Florida Add-on and non-motorist crash frequency and severity data from Florida. The applicability of the framework is illustrated through extensive policy scenario analysis.

Multivariate copula temporal modeling of intersection crash consequence metrics: A joint estimation of injury severity, crash type, vehicle damage and driver error.

This study employs a copula-based multivariate temporal ordered probit model to simultaneously estimate the four common intersection crash consequence metrics - driver error, crash type, vehicle damage and injury severity - by accounting for potential correlations due to common observed and unobserved factors, while also accommodating the temporal instability of model estimates over time. To this end, a comprehensive literature review of relevant studies was conducted; four different copula model specifications including Frank, Clayton, Joe and Gumbel were estimated to identify the dominant factors contributing to each crash consequence indicator; the temporal effects on model estimates were investigated; the elasticity effects of the independent variables with regard to all four crash consequence indicators were measured to express the magnitude of the effects of an independent variable on the probability change for each level of four indicators; and specific countermeasures were recommended for each of the contributing factors to improve the intersection safety. The model goodness-of-fit illustrates that the Joe copula model with the parameterized copula parameters outperforms the other models, which verifies that the injury severity, crash type, vehicle damage and driver error are significantly correlated due to common observed and unobserved factors and, accounting for their correlations, can lead to more accurate model estimation results. The parameterization of the copula function indicates that their correlation varies among different crashes, including crashes that occurred at stop-controlled intersections, four-leg intersections and crashes which involved drivers younger than 25. The model coefficient estimates indicate that the driver's age, driving under the influence of drugs and alcohol, intersection geometry and control types, and adverse weather and light conditions are the most critical factors contributing to severe crash consequences. The coefficient estimates of four-leg intersections, yield and stop-controlled intersections and adverse weather conditions varied over time, which indicates that the model estimation of crash data may not be stable over time and should be accommodated in crash prediction analysis. In the end, relevant countermeasures corresponding to law enforcement and intersection infrastructure design are recommended to all of the contributing factors identified by the model. It is anticipated that this study can shed light on selecting valid statistical models for crash data analysis, identifying intersection safety issues, and helping develop effective countermeasures to improve intersection safety.

Analysis of crash proportion by vehicle type at traffic analysis zone level: A mixed fractional split multinomial logit modeling approach with spatial effects.

In traffic safety literature, crash frequency variables are analyzed using univariate count models or multivariate count models. In this study, we propose an alternative approach to modeling multiple crash frequency dependent variables. Instead of modeling the frequency of crashes we propose to analyze the proportion of crashes by vehicle type. A flexible mixed multinomial logit fractional split model is employed for analyzing the proportions of crashes by vehicle type at the macro-level. In this model, the proportion allocated to an alternative is probabilistically determined based on the alternative propensity as well as the propensity of all other alternatives. Thus, exogenous variables directly affect all alternatives. The approach is well suited to accommodate for large number of alternatives without a sizable increase in computational burden. The model was estimated using crash data at Traffic Analysis Zone (TAZ) level from Florida. The modeling results clearly illustrate the applicability of the proposed framework for crash proportion analysis. Further, the Excess Predicted Proportion (EPP)-a screening performance measure analogous to Highway Safety Manual (HSM), Excess Predicted Average Crash Frequency is proposed for hot zone identification. Using EPP, a statewide screening exercise by the various vehicle types considered in our analysis was undertaken. The screening results revealed that the spatial pattern of hot zones is substantially different across the various vehicle types considered.

Latent segmentation based count models: Analysis of bicycle safety in Montreal and Toronto.

The study contributes to literature on bicycle safety by building on the traditional count regression models to investigate factors affecting bicycle crashes at the Traffic Analysis Zone (TAZ) level. TAZ is a traffic related geographic entity which is most frequently used as spatial unit for macroscopic crash risk analysis. In conventional count models, the impact of exogenous factors is restricted to be the same across the entire region. However, it is possible that the influence of exogenous factors might vary across different TAZs. To accommodate for the potential variation in the impact of exogenous factors we formulate latent segmentation based count models. Specifically, we formulate and estimate latent segmentation based Poisson (LP) and latent segmentation based Negative Binomial (LNB) models to study bicycle crash counts. In our latent segmentation approach, we allow for more than two segments and also consider a large set of variables in segmentation and segment specific models. The formulated models are estimated using bicycle-motor vehicle crash data from the Island of Montreal and City of Toronto for the years 2006 through 2010. The TAZ level variables considered in our analysis include accessibility measures, exposure measures, sociodemographic characteristics, socioeconomic characteristics, road network characteristics and built environment. A policy analysis is also conducted to illustrate the applicability of the proposed model for planning purposes. This macro-level research would assist decision makers, transportation officials and community planners to make informed decisions to proactively improve bicycle safety - a prerequisite to promoting a culture of active transportation.

Disentangling the influence of cell phone usage in the dilemma zone: An econometric approach.

This paper focuses on developing an analysis framework to study the impact of cell phone treatment (cell phone type and call status) on driver behavior in the presence of a dilemma zone. Specifically, we examine how the treatment influences the driver maneuver decision at the intersection (stop or cross) and the eventual success of the maneuver. For a stop maneuver, success is defined as stopping before the stop line. Similarly, for a cross maneuver, success is defined as clearing the intersection safely before the light turns red. The eventual success or failure of the driver's decision process is dependent on the factors that affected the maneuver decision. Hence it is important to recognize the interconnectedness of the stop or cross decision with its eventual success (or failure). Toward this end, we formulate and estimate a joint framework to analyze the stop/cross decision with its eventual success (or failure) simultaneously. The study is conducted based on driving simulator data provided online for the 2014 Transportation Research Board Data Contest at http://depts.washington.edu/hfsm/upload.php. The model is estimated to analyze drivers' behavior at the onset of yellow by employing exogenous variables from three broad categories: driver characteristics, cell phone attributes and driving attributes. We also generate probability surfaces to identify dilemma zone distribution associated with different cell phone treatment types. The plots clearly illustrate the impact of various cellphone treatments on driver dilemma zone behavior.

Pooling data from fatality analysis reporting system (FARS) and generalized estimates system (GES) to explore the continuum of injury severity spectrum.

Fatality Analysis Reporting System (FARS) and Generalized Estimates System (GES) data are most commonly used datasets to examine motor vehicle occupant injury severity in the United States (US). The FARS dataset focuses exclusively on fatal crashes, but provides detailed information on the continuum of fatality (a spectrum ranging from a death occurring within thirty days of the crash up to instantaneous death). While such data is beneficial for understanding fatal crashes, it inherently excludes crashes without fatalities. Hence, the exogenous factors identified as critical in contributing (or reducing) to fatality in the FARS data might possibly offer different effects on non-fatal crash severity levels when a truly random sample of crashes is considered. The GES data fills this gap by compiling data on a sample of roadway crashes involving all possible severity consequences providing a more representative sample of traffic crashes in the US. FARS data provides a continuous timeline of the fatal occurrences from the time to crash - as opposed to considering all fatalities to be the same. This allows an analysis of the survival time of victims before their death. The GES, on the other hand, does not offer such detailed information except identifying who died in the crash. The challenge in obtaining representative estimates for the crash population is the lack of readily available "appropriate" data that contains information available in both GES and FARS datasets. One way to address this issue is to replace the fatal crashes in the GES data with fatal crashes from FARS data thus augmenting the GES data sample with a very refined categorization of fatal crashes. The sample thus formed, if statistically valid, will provide us with a reasonable representation of the crash population. This paper focuses on developing a framework for pooling of data from FARS and GES data. The validation of the pooled sample against the original GES sample (unpooled sample) is carried out through two methods: (1) univariate sample comparison and (2) econometric model parameter estimate comparison. The validation exercise indicates that parameter estimates obtained using the pooled data model closely resemble the parameter estimates obtained using the unpooled data. After we confirm that the differences in model estimates obtained using the pooled and unpooled data are within an acceptable margin, we also simultaneously examine the whole spectrum of injury severity on an eleven point ordinal severity scale - no injury, minor injury, severe injury, incapacitating injury, and 7 refined categories of fatalities ranging from fatality after 30 days to instant death - using a nationally representative pooled dataset. The model estimates are augmented by conducting elasticity analysis to illustrate the applicability of the proposed framework.

Investigating the role of transportation models in epidemiologic studies of traffic related air pollution and health effects.

In two earlier case-control studies conducted in Montreal, nitrogen dioxide (NO2), a marker for traffic-related air pollution was found to be associated with the incidence of postmenopausal breast cancer and prostate cancer. These studies relied on a land use regression model (LUR) for NO2 that is commonly used in epidemiologic studies for deriving estimates of traffic-related air pollution. Here, we investigate the use of a transportation model developed during the summer season to generate a measure of traffic emissions as an alternative to the LUR model. Our traffic model provides estimates of emissions of nitrogen oxides (NOx) at the level of individual roads, as does the LUR model. Our main objective was to compare the distribution of the spatial estimates of NOx computed from our transportation model to the distribution obtained from the LUR model. A secondary objective was to compare estimates of risk using these two exposure estimates. We observed that the correlation (spearman) between our two measures of exposure (NO2 and NOx) ranged from less than 0.3 to more than 0.9 across Montreal neighborhoods. The most important factor affecting the "agreement" between the two measures in a specific area was found to be the length of roads. Areas affected by a high level of traffic-related air pollution had a far better agreement between the two exposure measures. A comparison of odds ratios (ORs) obtained from NO2 and NOx used in two case-control studies of breast and prostate cancer, showed that the differences between the ORs associated with NO2 exposure vs NOx exposure differed by 5.2-8.8%.

Examining driver injury severity in two vehicle crashes - a copula based approach.

A most commonly identified exogenous factor that significantly affects traffic crash injury severity sustained is the collision type variable. Most studies consider collision type only as an explanatory variable in modeling injury. However, it is possible that each collision type has a fundamentally distinct effect on injury severity sustained in the crash. In this paper, we examine the hypothesis that collision type fundamentally alters the injury severity pattern under consideration. Toward this end, we propose a joint modeling framework to study collision type and injury severity sustained as two dimensions of the severity process. We employ a copula based joint framework that ties the collision type (represented as a multinomial logit model) and injury severity (represented as an ordered logit model) through a closed form flexible dependency structure to study the injury severity process. The proposed approach also accommodates the potential heterogeneity (across drivers) in the dependency structure. Further, the study incorporates collision type as a vehicle-level, as opposed to a crash-level variable as hitherto assumed in earlier research, while also examining the impact of a comprehensive set of exogenous factors on driver injury severity. The proposed modeling system is estimated using collision data from the province of Victoria, Australia for the years 2006 through 2010.

Evaluating alternate discrete outcome frameworks for modeling crash injury severity.

This paper focuses on the relevance of alternate discrete outcome frameworks for modeling driver injury severity. The study empirically compares the ordered response and unordered response models in the context of driver injury severity in traffic crashes. The alternative modeling approaches considered for the comparison exercise include: for the ordered response framework-ordered logit (OL), generalized ordered logit (GOL), mixed generalized ordered logit (MGOL) and for the unordered response framework-multinomial logit (MNL), nested logit (NL), ordered generalized extreme value logit (OGEV) and mixed multinomial logit (MMNL) model. A host of comparison metrics are computed to evaluate the performance of these alternative models. The study provides a comprehensive comparison exercise of the performance of ordered and unordered response models for examining the impact of exogenous factors on driver injury severity. The research also explores the effect of potential underreporting on alternative frameworks by artificially creating an underreported data sample from the driver injury severity sample. The empirical analysis is based on the 2010 General Estimates System (GES) data base-a nationally representative sample of road crashes collected and compiled from about 60 jurisdictions across the United States. The performance of the alternative frameworks are examined in the context of model estimation and validation (at the aggregate and disaggregate level). Further, the performance of the model frameworks in the presence of underreporting is explored, with and without corrections to the estimates. The results from these extensive analyses point toward the emergence of the GOL framework (MGOL) as a strong competitor to the MMNL model in modeling driver injury severity.

Comparison of crashes during public holidays and regular weekends.

Traffic collisions and fatalities during the holiday festive periods are apparently on the rise in Alberta, Canada, despite the enhanced enforcement and publicity campaigns conducted during these periods. Using data from 2004 to 2008, this research identifies the factors that delineate between crashes that occur during public holidays and those occurring during normal weekends. We find that fatal and injury crashes are over-represented during holidays. Amongst the three risky behaviors targeted in the holiday blitzes (driver intoxication, unsafe speeding and restraint use), non-use of restraint is more prevalent whereas driver intoxication and unsafe speeding are less prevalent during holidays. The mixed results obtained suggest that it may be time to consider a more balanced approach to the enhanced enforcement and publicity campaigns.