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

A negative binomial Lindley approach considering spatiotemporal effects for modeling traffic crash frequency with excess zeros

Statistical analysis of traffic crash frequency is significant for figuring out the distribution pattern of crashes, predicting the development trend of crashes, formulating traffic crash prevention measures, and improving traffic safety planning systems. In recent years, the theory and practice for traffic safety management have shown that road crash data have characteristics such as spatial correlation, temporal correlation, and excess zeros. If these characteristics are ignored in the modeling process, it may seriously affect the fitting performance and prediction accuracy of traffic crash frequency models and even lead to incorrect conclusions. In this research, traffic crash data from rural two-way two-lane from four counties in Pennsylvania, USA was modeled considering the spatiotemporal effects of crashes. First, a negative binomial Lindley spatiotemporal effect model of crash frequency was constructed at the micro level; Simultaneously, the characteristics and problems of excess zeros and potential heterogeneity of the crash data were resolved; Finally, the effects of road characteristics on crash frequency were analyzed. The results indicate a significant spatial correlation between the crash frequency of adjacent road sections. Compared with the negative binomial model, the negative binomial Lindley model can better handle the excess zeros characteristics in traffic crash data. The model that considers both spatial correlation and temporal conditional autoregressive effects has the best fit for the observed data. In addition, for road sections that allow passing and have a speed limitation of not less than 50 miles per hour, the crash frequency corresponding to these sections is lower due to their good visibility and road conditions. The increase in average turning angle and intersection density on the horizontal curve of the road section corresponds to an increase in crash frequency.

Multi-objective extensive hypothesis testing for the estimation of advanced crash frequency models

Analyzing crash data is a complex and labor-intensive process that requires careful consideration of multiple interdependent modeling aspects, such as functional forms, transformations, likely contributing factors, correlations, and unobserved heterogeneity. Limited time, knowledge, and experience may lead to over-simplified, over-fitted, or misspecified models overlooking important insights. This paper proposes an extensive hypothesis testing framework including a multi-objective mathematical programming formulation and solution algorithms to estimate crash frequency models considering simultaneously likely contributing factors, transformations, non-linearities, and correlated random parameters. The mathematical programming formulation minimizes both in-sample fit and out-of-sample prediction. To address the complexity and non-convexity of the mathematical program, the proposed solution framework utilizes a variety of metaheuristic solution algorithms. Specifically, Harmony Search demonstrated minimal sensitivity to hyperparameters, enabling an efficient search for solutions without being influenced by the choice of hyperparameters. The effectiveness of the framework was evaluated using two real-world datasets and one synthetic dataset. Comparative analyses were performed using the two real-world datasets and the corresponding models published in literature by independent teams. The proposed framework showed its capability to pinpoint efficient model specifications, produce accurate estimates, and provide valuable insights for both researchers and practitioners. The proposed approach allows for the discovery of numerous insights while minimizing the time spent on model development. By considering a broader set of contributing factors, models with varied qualities can be generated. For instance, when applied to crash data from Queensland, the proposed approach revealed that the inclusion of medians on sharp curved roads can effectively reduce the occurrence of crashes, when applied to crash data from Washington, the simultaneous consideration of traffic volume and road curvature resulted in a notable reduction in crash variances but an increase in crash means.

Bayesian multilevel hidden Markov models identify stable state dynamics in longitudinal recordings from macaque primary motor cortex

Neural populations, rather than single neurons, may be the fundamental unit of cortical computation. Analysing chronically recorded neural population activity is challenging not only because of the high dimensionality of activity but also because of changes in the signal that may or may not be due to neural plasticity. Hidden Markov models (HMMs) are a promising technique for analysing such data in terms of discrete latent states, but previous approaches have not considered the statistical properties of neural spiking data, have not been adaptable to longitudinal data, or have not modelled condition-specific differences. We present a multilevel Bayesian HMM addresses these shortcomings by incorporating multivariate Poisson log-normal emission probability distributions, multilevel parameter estimation and trial-specific condition covariates. We applied this framework to multi-unit neural spiking data recorded using chronically implanted multi-electrode arrays from macaque primary motor cortex during a cued reaching, grasping and placing task. We show that, in line with previous work, the model identifies latent neural population states which are tightly linked to behavioural events, despite the model being trained without any information about event timing. The association between these states and corresponding behaviour is consistent across multiple days of recording. Notably, this consistency is not observed in the case of a single-level HMM, which fails to generalise across distinct recording sessions. The utility and stability of this approach is demonstrated using a previously learned task, but this multilevel Bayesian HMM framework would be especially suited for future studies of long-term plasticity in neural populations.

Do footbridge and underpass improve pedestrian safety? A Hong Kong case study using three-dimensional digital map of pedestrian network

Hong Kong is a compact city with high activity and travel intensity. In the past decades, many footbridges and underpasses were installed to reduce the pedestrian-vehicle conflicts on urban roads. However, it is rare that the effects of configuration of pedestrian network on pedestrian crashes are investigated. In Hong Kong, many footbridges and underpasses are connected to major transport hubs and commercial building development and become parts of giant elevated and underground walkway systems. It is challenging to characterize such a complicated pedestrian network. In this study, a three-dimensional digital map is applied to estimate the connectivity and accessibility of pedestrian network, and measure the relationship between pedestrian network characteristics and pedestrian safety at the macroscopic level. Hence, the effects of footbridge and underpass on pedestrian safety are examined. For example, comprehensive built environment, pedestrian network, traffic, and crash data are aggregated to 379 grids (0.5 km × 0.5 km). Then, multivariate Poisson lognormal regression approach is applied to model fatal and severe injury (FSI) and slight injury pedestrian crashes, with which the effects of unobserved heterogeneity, spatial correlation, and correlation between crash counts are accounted. Results indicate that population density, traffic volume, walking trip, footpath density, node density, number of vertices per footpath segment, bus stop, metro exit, residential area, commercial area, and government and utility area are positively associated with pedestrian crashes. In contrast, average gradient, accessibility of footbridge, accessibility of underpass, and number of crossings per road segment are negatively associated with pedestrian crashes. In other word, pedestrian safety would be improved when footbridge and underpass are more accessible. Findings have implications for the design and planning of pedestrian network to promote walkability and improve pedestrian safety.

Multi-vehicle safety functions for freeway weaving segments using lane-level traffic data

This study develops Safety Performance Functions (SPFs) for freeway weaving segments. Due to the coexistence of three different movements including through, merging, and divering traffic, the probability of crashes in weaving segments is higher compared to other segment types. Further, the traffic flow in this section is the most unstable. Hence, to analyze detailed traffic conditions, this study utilized lane-level traffic data. The SPFs were developed using the Poisson Lognormal (PLN) regression model technique. The results showed that different traffic parameters were significant based on the types of crashes. For the rear-end crashes model, more general traffic conditions of the weaving segment were found to be significantly associated with the crash frequency such as the natural logarithm of average speed of through lanes. Nevertheless, for the sideswipe and angle crashes models, the traffic variables which are directly related to the weaving movements were selected as significant factors such as the off-ramp volume ratio, and standard deviation of speed of the rightmost lane. The results presented in this study can be meaningful in that they can serve as a basis for the weaving segments related safety evaluation studies. In addition, the developed models' results can be a great source to establish operational strategies to improve traffic safety on freeway weaving segments.

Effect of transit-oriented design on pedestrian and cyclist safety using bivariate spatial models

INTRODUCTION

Walking and cycling for transportation provide immense benefits (e.g., health, environmental, social). However, pedestrians and bicyclists are the most vulnerable segment of the traveling public due to the lack of protective structure and difference in body mass compared with motorized vehicles. Numerous studies are dedicated to enhancing active transportation modes, but very few studies are devoted to the safety analysis of the transit stops, which serve as the important modal interface for pedestrians and bicyclists.

METHOD

This study bridges the gap by developing joint models based on the multivariate conditional autoregressive (MCAR) priors with distance-oriented neighboring weight matrix. For this purpose, transit-oriented design (TOD) related data in Los Angeles County were used for model development. Feature selection relying on both random forest (RF) and correlation analysis was employed, which leads to different covariates inputs to each of the two joint models, resulting in increased model flexibility. An integrated nested Laplace approximation (INLA) algorithm was adopted due to its fast, yet robust, analysis. For a comprehensive comparison of the predictive accuracy of models, different evaluation criteria were utilized.

RESULTS

The results demonstrate that models with correlation effect perform much better than the models without a correlation of pedestrians and bicyclists. The joint models also aid in the identification of the significant covariates contributing to the safety of each of the two active transportation modes. The findings show that population density, employment density, and bus stop density positively influence bicyclist-involved crashes, suggesting that an increase in population, employment, or the number of bus stops leads to more active modes involved collisions.

PRACTICAL APPLICATIONS

The findings of this study may prove helpful in the development and implementation of the safety management process to improve the roadway environment for the active modes in the long run.

Modeling the Impact of Driving Styles on Crash Severity Level Using SHRP 2 Naturalistic Driving Data

Previous studies have examined driving styles and how they are associated with crash risks relying on self-report questionnaires to categorize respondents based on pre-defined driving styles. Naturalistic driving studies provide a unique opportunity to examine this relationship differently. The current study aimed to study how driving styles, derived from real-road driving, may relate to crash severity. To study the relationship, this study retrieved safety critical events (SCEs) from the SHRP 2 database and adopted joint modelling of the number of the aggregated crash severity levels (crash vs. non-crash) using the Diagonal Inflated Bivariate Poisson (DIBP) model. Variables examined included driving styles and various driver characteristics. Among driving styles examined, styles of maintenance of lower speeds and more adaptive responses to driving conditions were associated with fewer crashes given an SCE occurred. Longer driving experiences, more miles driven last year, and being female also reduced the number of crashes. Interestingly, older drivers were associated with both an increased number of crashes and increased number of non-crash SCEs. Future work may leverage more variables from the SHRP 2 database and widen the scope to examine different traffic conditions for a more complete picture of driving styles.

Effect of urban street trees on pedestrian safety: A micro-level pedestrian casualty model using multivariate Bayesian spatial approach

In the past decades, trees were considered roadside hazard. Street trees were removed to provide clear zone and improve roadside safety. Nowadays, street trees are considered to play an important role in urban design. Also, street tree is considered a traffic calming measure. Studies have examined the effects of urban street trees on driver perception, driving behaviour, and general road safety. However, it is rare that the relationship between urban street trees and pedestrian safety is investigated. In this study, a micro-level frequency model is established to evaluate the effects of tree density and tree canopy cover on pedestrian injuries, accounting for pedestrian crash exposure based on comprehensive pedestrian count data from a state in Australia, Melbourne. In addition, effects of road geometry, traffic characteristics, and temporal distribution are also considered. Furthermore, effects of spatial dependency and correlation between pedestrian casualty counts of different injury severity levels are accounted using a multivariate Bayesian spatial approach. Results indicate that road width, bus stop, tram station, on-street parking, and 85th percentile speed are positively associated with pedestrian casualty. In contrast, pedestrian casualty decreases when there is a pedestrian crosswalk and increases in tree density and canopy. Also, time variation in pedestrian injury risk is significant. To sum up, urban street trees should have favorable effect on pedestrian safety. Findings are indicative to optimal policy strategies that can enhance the walking environment and overall pedestrian safety. Therefore, sustainable urban and transport development can be promoted.

Influence of Intersection Density on Risk Perception of Drivers in Rural Roadways: A Driving Simulator Study

With the aim of maintaining a decent level of accessibility, the presence of intersections, often in high numbers, is one of the typical features of rural roads. However, evidence from literature shows that increasing intersection density increases the risk of accidents. Accident analysis literature regarding intersection density primarily consists of accident prediction models which are a useful tool for measuring safety performance of roads, but the literature is lacking in terms of evaluation of driver behavior using direct measurements of driver performance. This study focuses on the influence of intersection density on the risk perception of drivers through experiments carried out with a driving simulator. A virtual driving environment of a rural roadway was constructed. The road consisted of segments featuring extra-urban and village driving environments with varying intersection density level. Participants were recruited to drive through this virtual driving environment. Various driver performance measures such as vehicle speed and brake and gas pedal usage were collected from the experiment and then processed for further analysis. Results indicate an increase in driver’s perceived risk when the intersection density increased, according with the findings from the accident prediction modeling literature. However, at the same time, this driving simulator study revealed some interesting insights about oscillating perceived risk among drivers in the case of mid-level intersection separation distances. Beyond the accident research domain, findings from this study can also be useful for engineers and transportation agencies associated with access management to make more informed decisions.

A comprehensive analysis on the effects of signal strategies, intersection geometry, and traffic operation factors on right-turn crashes at signalised intersections: An application of hierarchical crash frequency model

Right-turn movements (equivalent to left turn movements for countries that drive on the right) at intersections are among the most complex driving maneuvers and require a high level of attention for turning across (potentially) oncoming traffic by accepting a safe gap. Not surprisingly, right-turn-involved crashes are one of the most frequent collision types at intersections (e.g., 42% of all signalised intersection crashes in Queensland, Australia). Unfortunately, the causes and contributing factors to right-turn crashes are not well understood, particularly the effect of right-turn signal strategies on the crash risk. In the safety literature, signal strategies are coarsely considered in two generic categories-protected right-turns and permitted right-turns. In reality, right-turn signal strategies could be of various types (usually 5) based on the level of intersection complexity and potential traffic conflicts. The effects of these signal strategies, along with the geometric and traffic factors, have not been well studied. To fill this gap, this study investigates the effects of right-turn signal strategies, intersection geometry and traffic operations factors on right-turn crashes at signalised intersections. To achieve this aim, crash frequency models were estimated using crash data from 221 signalised intersections in Queensland from the years spanning 2012 to 2018. Hierarchical Poisson Regression Models (random intercept models) were employed to capture the hierarchical structure of influences on crashes, with upper-level capturing intersection characteristics and lower-level capturing approach characteristics. The hierarchical model structure, disaggregate exposure variables, and signal strategies examined in this study give rise to an entirely unique study in the literature.

Investigating risk factors associated with pedestrian crash occurrence and injury severity in Texas

OBJECTIVE

This study investigates various risk factors associated with pedestrian crash occurrence and injury severity based on 78,497 reported pedestrian-involved crashes across Texas from 2010 through 2019.

METHODS

Crashes are mapped to over 708,738 road segments, along with road design, land use, transit, hospital, rainfall, and other location features. Negative binomial models examine the association between pedestrian crash frequency and various contributing factors, and a heteroskedastic ordered probit model investigates the severity of injuries at the individual crash level.

RESULTS

Results from this study show the practical significance of microlevel variables in predicting pedestrian crashes. Proximity to schools and hospitals and presence of transit are all associated with higher pedestrian crash frequencies yet are rarely included in other models. Total pedestrian crash and fatal crash counts rise with the number of lanes, population, and job densities, though greater median and shoulder widths provide some protection. Higher speed limits are associated with lower crash frequencies but more deaths. Pedestrian crashes are more likely to be severe and fatal at night (8 p.m. to 5 a.m.), without overhead lighting, and when involved pedestrians and/or drivers are intoxicated. Use of light-duty trucks also significantly increases risk of severe or fatal pedestrian injury. Though newer vehicle safety features may be argued to lower crash severity or protect vehicle occupants, newer crash-involved vehicles in Texas are not found to deliver less severe pedestrian injury. Pedestrian and driver characteristics-both age and gender-are practically (and statistically) significant. Injury severity rises with pedestrian age, yet younger and/or female pedestrians on straight roadways, off the state (and interstate) highway system, and in the presence of a traffic control device (stop sign or signal) are less likely to be seriously injured, on average.

CONCLUSIONS

Findings underscore the benefit of enhanced vehicle safety features for pedestrians, campaigns against driving and walking while intoxicated, improved roadway design, enforcement of safety countermeasures near schools and bus stops, and installment of additional traffic controls and streetlights wherever more pedestrians exist.

Overcoming challenges in crash prediction modeling using discretized duration approach: An investigation of sampling approaches

Until recently, statistical approaches used for real-time crash prediction modeling were limited to case-control design and "sampling of alternatives" approaches. A recent study has developed a duration-based real-time crash prediction model capable of incorporating dynamic (time-varying) covariates within its framework. The modeling approach discretizes the duration between crashes into equal time intervals which can be modeled as alternatives in a multinomial logit framework. The approach, however, requires a reformulation of the original crash dataset to fit its modeling framework which results in considerably large data making model estimation computationally demanding. Additionally, validation of the model in the original study is based on crash data from just one interstate, I-405, assuming homogenous highway segments each 5 miles in length. This study improves upon the original study by investigating sampling techniques that can be applied to the reformulated data to reduce computational load using 2019 crash data from two interstates, I-40 and I-55, in Memphis, Tennessee. Furthermore, discretization of inter-crash duration is undertaken following non-homogenous segmentation of the interstates that is based on highway geometry, terrain, and posted speed limit. To accomplish the study objectives, a relatively small future window of 1 h with 15-minute time intervals is used to discretize the inter-crash duration and obtain the reformulated data. Sampling of crashes for model estimation is then done at the crash, epoch, and segment levels to answer the question of which sampling technique (by crash, epoch, or segment) would result in reasonable accuracy when compared with the complete (100%) data. Results show that 25% of samples drawn at the epoch level can result in a considerable reduction of computational load while providing reasonably consistent estimates.

Predicting and Analyzing Road Traffic Injury Severity Using Boosting-Based Ensemble Learning Models with SHAPley Additive exPlanations

Road traffic accidents are one of the world’s most serious problems, as they result in numerous fatalities and injuries, as well as economic losses each year. Assessing the factors that contribute to the severity of road traffic injuries has proven to be insightful. The findings may contribute to a better understanding of and potential mitigation of the risk of serious injuries associated with crashes. While ensemble learning approaches are capable of establishing complex and non-linear relationships between input risk variables and outcomes for the purpose of injury severity prediction and classification, most of them share a critical limitation: their “black-box” nature. To develop interpretable predictive models for road traffic injury severity, this paper proposes four boosting-based ensemble learning models, namely a novel Natural Gradient Boosting, Adaptive Gradient Boosting, Categorical Gradient Boosting, and Light Gradient Boosting Machine, and uses a recently developed SHapley Additive exPlanations analysis to rank the risk variables and explain the optimal model. Among four models, LightGBM achieved the highest classification accuracy (73.63%), precision (72.61%), and recall (70.09%), F1-scores (70.81%), and AUC (0.71) when tested on 2015–2019 Pakistan’s National Highway N-5 (Peshawar to Rahim Yar Khan Section) accident data. By incorporating the SHapley Additive exPlanations approach, we were able to interpret the model’s estimation results from both global and local perspectives. Following interpretation, it was determined that the Month_of_Year, Cause_of_Accident, Driver_Age and Collision_Type all played a significant role in the estimation process. According to the analysis, young drivers and pedestrians struck by a trailer have a higher risk of suffering fatal injuries. The combination of trailers and passenger vehicles, as well as driver at-fault, hitting pedestrians and rear-end collisions, significantly increases the risk of fatal injuries. This study suggests that combining LightGBM and SHAP has the potential to develop an interpretable model for predicting road traffic injury severity.

A Review of Incident Prediction, Resource Allocation, and Dispatch Models for Emergency Management

In the last fifty years, researchers have developed statistical, data-driven, analytical, and algorithmic approaches for designing and improving emergency response management (ERM) systems. The problem has been noted as inherently difficult and constitutes spatio-temporal decision making under uncertainty, which has been addressed in the literature with varying assumptions and approaches. This survey provides a detailed review of these approaches, focusing on the key challenges and issues regarding four sub-processes: (a) incident prediction, (b) incident detection, (c) resource allocation, and (c) computer-aided dispatch for emergency response. We highlight the strengths and weaknesses of prior work in this domain and explore the similarities and differences between different modeling paradigms. We conclude by illustrating open challenges and opportunities for future research in this complex domain.

Structural anatomy and temporal trends of road accident research: Full-scope analyses of the field

INTRODUCTION

Scholarly research on road accidents over the past 50 years has generated substantial literature. We propose a robust search strategy to retrieve and analyze this literature.

METHOD

Analyses was focused on estimating the size of this literature and examining its intellectual anatomy and temporal trends using bibliometric indicators of its articles.

RESULTS

The size of the literature is estimated to have exceeded N = 25,000 items as of 2020. At the highest level of aggregation, patterns of term co-occurrence in road accident articles point to the presence of six major divisions: (i) law, legislation & road trauma statistics; (ii) vehicular safety technology; (iii) statistical modelling; (iv) driving simulator experiments of driving behavior; (v) driver style and personality (social psychology); and (vi) vehicle crashworthiness and occupant protection division. Analyses identify the emergence of various research clusters and their progress over time along with their respective influential entities. For example, driver injury severity " and crash frequency show distinct characteristics of trending topics, with research activities in those areas notably intensified since 2015 Also, two developing clusters labelled autonomous vehicle and automated vehicle show distinct signs of becoming emerging streams of road accident literature.

CONCLUSIONS

By objectively documenting temporal patterns in the development of the field, these analyses could offer new levels of insight into the intellectual composition of this field, its future directions, and knowledge gaps. Practical Applications: The proposed search strategy can be modified to generate specific subsets of this literature and assist future conventional reviews. The findings of temporal analyses could also be instrumental in informing and enriching literature review sections of original research articles. Analyses of authorships can facilitate collaborations, particularly across various divisions of accident research field.

Estimation of crash type frequencies on individual collector roadway segments

Individual collision types have different underlying causes and thus the relationships between roadway/traffic characteristics and crash frequency are likely to differ across unique collision types. One way these different influences have been studied is by developing separate statistical models for each collision type. While this is the most straightforward approach, developing collision-specific models can be very tedious and can produce unreliable estimates for collision types that are less frequently observed. Moreover, ignoring correlations between different collision types may result in biased and inefficient parameter estimation. To overcome these limitations, researchers have adopted a multivariate approach that explicitly accounts for the correlation among individual collision types. As an alternative to multivariate approach, two-stage approaches have been proposed in which one model is estimated to predict total crash frequency and its prediction is combined with another model, used to predict the proportions of different collision types. More efficient one-stage joint models, in which both the frequency and proportion models are estimated simultaneously and predictions are provided more directly, have also been proposed for macro-level analysis. This study investigates the performance of this joint model paradigm in analyzing unique collision type frequencies on individual road segments. For this, a joint negative binomial-multinomial fractional split (NB-MFS) model is used. Moreover, this study also proposes the use of a multinomial logit (MNL) model to estimate the proportion of different collision types. As total crash frequency NB model and MNL model utilize different datasets, a two-stage estimation process is required, which leads to the two-stage NB-MNL model proposed here. The performance of proposed model is compared with that of collision-specific NB models, multivariate negative binomial (MVNB) model, and NB-MFS model in predicting crash frequency by collision type on two-way two-lane urban-suburban collector roadway segments in Pennsylvania. The goodness of fit statistics show that the NB-MNL model performs better than collision-specific NB models, MVNB model and joint NB-MFS model and is thus a promising approach in predicting crash frequency by collision type.

Applying a Bayesian multivariate spatio-temporal interaction model based approach to rank sites with promise using severity-weighted decision parameters

Ranking sites with promise is an essential step for cost-effective engineering improvement on roadway traffic safety. This study proposes a Bayesian multivariate spatio-temporal interaction model based approach for ranking sites. The severity-weighted crash frequency and crash rate are used as the decision parameters. The posterior expected rank and posterior mean of the decision parameters are adopted as the statistical criteria. The proposed approach is applied to rank road segments on Kaiyang Freeway in China, which is conducted via programming in the freeware WinBUGS. The results of Bayesian estimation and assessment indicate that incorporating spatio-temporal correlations and interactions into the crash frequency model significantly improves the overall goodness-of-fit performance and affects the identified crash-contributing factors and the estimated safety effects for each severity level. With respect to the ranking results, significant differences are found between those generated from the proposed approach and those generated from the naïve ranking approach and a Bayesian approach based on the multivariate Poisson-lognormal model. Besides, the ranks under the posterior mean criterion are found generally consistent with those under the posterior expected rank criterion.

Understanding how relationships between crash frequency and correlates vary for multilane rural highways: Estimating geographically and temporally weighted regression models

Safety Performance Functions (SPFs) are critical tools in the management of highway safety projects. SPFs are used to predict the average number of crashes per year at a location, such as a road segment or an intersection. The Highway Safety Manual (HSM) provides default safety performance functions (SPFs), but it is recommended that states in the U.S. develop jurisdiction-specific SPFs using local crash data. To do this for the state of Tennessee, crash and road inventory data were integrated for multi-lane rural highway segments for the years 2013-2017. In addition to developing SPFs similar to those contained in the HSM, this study applied a new methodology to capture variation in crashes in both space and time. Specifically, Geographically and Temporally Weighted Regression (GTWR) models for the localization of SPFs were developed. The new methodology incorporates temporal aspects of crashes in the models because the impact of a specific variable on crash frequency may vary over time due to several reasons. Results indicate that GTWR models remarkably outperform the traditional regression models by capturing spatio-temporal heterogeneity. Most parameter estimates were found to vary substantially across space and time. In other words, the association of contributing variables with the number of crashes can vary from one region or period of time to another. This finding weakens the idea of transferring default SPFs to other states and applying a single localized SPF to all regions of a state. Enabled by growing computational power, these results emphasize the importance of accounting for spatial and temporal heterogeneity and developing highly localized SPFs. The methodology of this study can be used by researchers to follow the temporal trend and location of critical factors to identify sites for safety improvements.

Using worker's naturalistic response to determine and analyze work zone crashes in the presence of work zone intrusion alert systems

Work zone Intrusion Alert Systems (WZIAS) are alert mechanisms that detect and alert workers of vehicles intruding into a work zone. These systems pre-dominantly employ two components-sensors placed near the work zone perimeter that detect intrusions, and alarms placed closed to or carried by the workers that alerts them. This study investigates the association between layout of these components for three WZIAS on work zone crashes based on worker reaction. Also, the key determinants of work zone crashes in presence of the WZIAS is identified using survival analysis. The ideal deployment strategy and use case scenarios for the three WZIAS is presented based on the findings of the study. The systems were subjected to rigorous testing that emulated intrusions to record worker reaction and determine occurrence of crashes. Analysis of results indicate that the key determinants of work zone crashes are speed of the intruding vehicle, distance between the sensor and worker, and accuracy of a system in detecting intrusions and alerting workers. Results from field experiments suggest that identification of appropriate use cases for WZIAS is necessary to ensure they work effectively. Based on the findings from this study it is suggested that current guidelines on work zones be modified to standardize WZIAS setup.

Incorporating accident liability into crash risk analysis: A multidimensional risk source approach

In the field of traffic safety, the occurrence of accidents remains a cause of concern for road regulators as well as users. Exploring risk factors inducing the accidents and quantifying the accident risk will not only benefit the prevention and control of traffic accidents but also assist in developing effective risk propagation model for road accidents. This study uses detailed accident record data to mine the risk factors affecting the occurrence of accidents, and quantify the accident risk under the combination of risk factors. First, by reviewing relevant literature and analyzing historical accident, we construct a multi-dimension characterization framework of risk factors with bi-level structure. The Human Factors Analysis and Classification System (HFACS) is applied to supplement and improve the framework. Next, under this framework, we identify the risk factors in traffic accident record, and analyze the statistical characteristics from the level of risk sources and risk characteristics. Then, the concept of accident liability weight is proposed to measure the impact of risk factors on accident occurrence. Through the liability affirmation of risk factors, the accident probability are updated. Last, we establish an accident risk quantify model (ARQM) based on the mean mutual information to compare the likelihood of accidents in different scenarios. In addition, we compare the accident probability and risk under equivalent liability and liability affirmation, as well as give some fundamental ideas regarding how to effectively prevent accidents.

Fusing crash data and surrogate safety measures for safety assessment: Development of a structural equation model with conditional autoregressive spatial effect and random parameters

Most existing efforts to assess safety performance require sufficient crash data, which generally takes a few years to collect and suffers from certain limitations (such as long data collection time, under-reporting issue and so on). Alternatively, the surrogate safety measure (SSMs) based approach that can assess traffic safety by capturing the more frequent "near-crash" situations have been developed, but it is criticized for the potential sampling and measurement errors. This study proposes a new safety performance measure-Risk Status (RS), by fusing crash data and SSMs. Real-world connected vehicle data collected in the Safety Pilot Model Deployment (SPMD) project in Ann Arbor, Michigan is used to extract SSMs. With RS treated as a latent variable, a structural equation model with conditional autoregressive spatial effect and corridor-level random parameters is developed to model the interrelationship among RS, crash frequency, risk identified by SSMs, and contributing factors. The modeling results confirm the proposed interrelationship and the necessity to account for both spatial autocorrelation and unobserved heterogeneity. RS can integrate both crash frequency and SSMs together while controlling for observed and unobserved factors. RS is found to be a more reliable criterion for safety assessment in an implementation case of hotspot identification.

Spatial differentiation of road safety in Europe based on NUTS-2 regions

Road safety varies significantly across the regions in Europe. To understand the factors behind this differentiation and the effects they have, data covering 263 NUTS-2 (Nomenclature of Territorial Units for Statistics) regions across Europe (European Union and Norway) have been analysed. The assessment was made using Geographically Weighted Regression (GWR). As a dependent variable the Road Fatality Rate (RFR - number of fatalities in a given year per one million population of the region) was used. The GWR was developed from 2014 data and took account of variables that characterise economic, infrastructural and social development. The model was validated using 2016-2018 data. The following factors were found to be statistically significant: gross domestic product per person (GDPPC), number of passenger cars per inhabitant (MRPC), share of passenger vehicles (PPC), life expectancy at birth (LIFE), as well as variables related to the border of the regions, innerborder (IB) and outerborder (OB). Results suggest that the GWR has an advantage over the global linear model which does not address regional proximity. The model allows for identification of the differences in the level of road safety in regions, estimated on the basis of the RFR and the available data in Eurostat databases. This in turn allows for indicating regions in which activities to improve road safety should have the highest priority. The model shows a large spatial diversity of factors affecting the RFR, which indicates the need to take different actions to improve road safety depending on the region. The results suggest that the GWR model can be useful for predicting and more efficient management of road safety at the regional level in Europe.

Highway safety assessment and improvement through crash prediction by injury severity and vehicle damage using Multivariate Poisson-Lognormal model and Joint Negative Binomial-Generalized Ordered Probit Fractional Split model

INTRODUCTION

Predicting crash counts by severity plays a dominant role in identifying roadway sites that experience overrepresented crashes, or an increase in the potential for crashes with higher severity levels. Valid and reliable methodologies for predicting highway accidents by severity are necessary in assessing contributing factors to severe highway crashes, and assisting the practitioners in allocating safety improvement resources.

METHODS

This paper uses urban and suburban intersection data in Connecticut, along with two sophisticated modeling approaches, i.e. a Multivariate Poisson-Lognormal (MVPLN) model and a Joint Negative Binomial-Generalized Ordered Probit Fractional Split (NB-GOPFS) model to assess the methodological rationality and accuracy by accommodating for the unobserved factors in predicting crash counts by severity level. Furthermore, crash prediction models based on vehicle damage level are estimated using the same two methodologies to supplement the injury severity in estimating crashes by severity when the sample mean of severe injury crashes (e.g., fatal crashes) is very low.

RESULTS

The model estimation results highlight the presence of correlations of crash counts among severity levels, as well as the crash counts in total and crash proportions by different severity levels. A comparison of results indicates that injury severity and vehicle damage are highly consistent.

CONCLUSIONS

Crash severity counts are significantly correlated and should be accommodated in crash prediction models. Practical application: The findings of this research could help select sound and reliable methodologies for predicting highway accidents by injury severity. When crash data samples have challenges associated with the low observed sampling rates for severe injury crashes, this research also confirmed that vehicle damage can be appropriate as an alternative to injury severity in crash prediction by severity.

Risk assessment of water resources pollution from transporting of oil hazardous materials (Sanandaj-Marivan road, Kurdistan Province, Iran)

Water pollution is one of the most important environmental challenges and also one of the main causes of death in the world. Transporting oil products on roads by trucks and their accidents lead to the release of these chemicals into the environment, resulting in water resources pollution. Thus, the main goal of this study is to evaluate the risk assessment of the water resources pollution in the road of Sanandaj to Marivan, Kurdistan province, Iran. Six scenarios for four types of hazardous materials in two seasons of the years were considered. The road was then segmented, and the probability of accidents in each segment was calculated by the Poisson regression method. Two scenarios were selected for analysis since truck accidents had happened mainly in spring (scenario 1) and winter (scenario 4). According to the results, the total risk of water contamination path is 20%very low, 19% low, 29% moderate, 28% high, and 4% very high. Also, according to scenario 1, 14% of the total area of the study area is very low risk, 23% low risk, 15% medium risk, 6% high risk, and 42% are very high risk. Based on scenario 4, 39% of the total area of the study area has a very low risk, 44% low risk, 13% medium risk, 4% high risk. This simply means that this road is not very suitable for transporting hazardous oil products.

Identifying the Factors That Increase the Probability of an Injury or Fatal Traffic Crash in an Urban Context in Jordan

The lack of robust studies carried out on urban roads in developing countries makes it difficult to enhance traffic safety, ensuring sustainable roads and cities. This study analyzes the contribution of a number of explanatory variables behind crashes involving injuries on arterial roads in Irbid (Jordan). Five binary logistic regression models were calibrated for a crash dataset from 2014–2018: one for the full database, and the others for the four main crash causes identified by Jordanian Traffic Police reports. The models show that whatever the crash cause, the three most significant factors linked to an injury or fatality lie in urban road sections that are in large-scale neighborhood areas, have fewer than six accesses per kilometer, and have a low traffic volume (under 500 veh/h/ln). Some of these results agree with previous studies in other countries. Jordan’s governmental agencies concerned with urban road safety might use these results to develop appropriate plans and implement priority actions for each crash cause, in addition to undertaking further research for comparative purposes.

Fifty Years of Accident Analysis & Prevention: A Bibliometric and Scientometric Overview

Accident Analysis & Prevention (AA&P) is a leading academic journal established in 1969 that serves as an important scientific communication platform for road safety studies. To celebrate its 50^th anniversary of publishing outstanding and insightful studies, a multi-dimensional statistical and visualized analysis of the AA&P publications between 1969 and 2018 was performed using the Web of Science (WoS) Core Collection database, bibliometrics and mapping-knowledge-domain (MKD) analytical methods, and scientometric tools. It was shown that the annual number of AA&P's publications has grown exponentially and that over the course of its development, AA&P has been a leader in the field of road safety, both in terms of innovation and dissemination. By determining its key source countries and organizations, core authors, highly co-cited published documents, and high burst-strength publications, we showed that AA&P's areas of focus include the "effects of hazard and risk perception on driving behavior", "crash frequency modeling analysis", "intentional driving violations and aberrant driving behavior", "epidemiology, assessment and prevention of road traffic injuries", and "crash-injury severity modeling analysis". Furthermore, the key burst papers that have played an important role in advancing research and guiding AA&P in new directions - particularly those in the fields of crash frequency and crash-injury severity modeling analyses were identified. Finally, a modified Haddon matrix in the era of intelligent, connected and autonomous transportation systems is proposed to provide new insights into the emerging generation of road safety studies.

A Bayesian spatial Poisson-lognormal model to examine pedestrian crash severity at signalized intersections

Reducing nonmotorized crashes requires a profound understanding of the causes and consequences of the crashes at the facility level. Generally, existing literature on bicyclists and pedestrian crash models suffers from two distinct problems: lack of exposure/volume data and inadequacy in capturing potential correlations across various crash aspects. To develop a robust framework for pedestrian crash analysis, this research employed a multivariate model across multiple pedestrian crash severities incorporating a crucial piece of information: pedestrian exposure. A multivariate spatial (conditional autoregressive) Poisson-lognormal model in a Bayesian framework was developed to examine the significant factors influencing the fatal, incapacitating injury (or suspected serious injury), and non-incapacitating injury pedestrian crashes at 409 signalized intersections in the Austin area. Various explanatory variables were used to examine the pedestrian crashes, including traffic characteristics, road geometry, built environment features, and pedestrian exposure volume at intersections, which was estimated through a direct demand model as part of the study. Model results revealed valuable insights. The superior performance of the multivariate model over the univariate model emphasized the need to jointly model multiple pedestrian crash severities. The results showed the significant positive influence of speed limit on fatal pedestrian crashes and revealed that both incapacitating and non-incapacitating injury crashes increase with increasing motorized traffic volume. Bus stop presence was found to have a negative influence on incapacitating injury crashes and a positive influence on non-incapacitating injury crashes. Moreover, the pedestrian volume at intersections positively influences non-incapacitating injury crashes. The difference in influence across crash types warrants careful and focused policy design of intersections to reduce pedestrian crashes of all severity types.

A systematic assessment of the use of opponent variables, data subsetting and hierarchical specification in two-party crash severity analysis

Road crashes impose an important burden on health and the economy. Numerous efforts have been undertaken to understand the factors that affect road collisions in general, and the severity of crashes in particular. In this literature several strategies have been proposed to model interactions between parties in a crash, including the use of variables regarding the other party (or parties) in the collision, data subsetting, and estimating models with hierarchical components. Since no systematic assessment has been conducted of the performance of these strategies, they appear to be used in an ad-hoc fashion in the literature. The objective of this paper is to empirically evaluate ways to model party interactions in the context of crashes involving two parties. To this end, a series of models are estimated using data from Canada's National Collision Database. Three levels of crash severity (no injury/injury/fatality) are analyzed using ordered probit models and covariates for the parties in the crash and the conditions of the crash. The models are assessed using predicted shares and classes of outcomes, and the results highlight the importance of considering opponent effects in crash severity analysis. The study also suggests that hierarchical (i.e., multi-level) specifications and subsetting do not necessarily perform better than a relatively simple single-level model with opponent-related factors. The results of this study provide insights regarding the performance of different modelling strategies, and should be informative to researchers in the field of crash severity.

Incorporating Bayesian methods into the propensity score matching framework: A no-treatment effect safety analysis

The propensity score matching method has been used to estimate safety countermeasure (treatment) effects from observational crash data. Within the counterfactual framework, propensity score matching is used to balance the covariates between treatment and control groups. Recent studies in traffic safety research have demonstrated the strength of this method in reducing the bias caused by treatment site selection. However, several general issues associated with safety effect estimates may still influence the effectiveness and robustness of this method. In the present study, Bayesian methods were integrated into the propensity score matching method. Bayesian models are known for their ability to capture heterogeneity and modeling uncertainty. This may help mitigate unobserved variable effects in the roadway and crash data. Furthermore, the sampling-based algorithm used for Bayesian estimation yields more consistent estimates in small region analysis than estimates from frequentist modeling. In this study, a dataset that was used to evaluate the safety effects of the dual application of shoulder and centerline rumble strips on two-lane rural highways was acquired. Only data from the before treatment period were used in a no-treatment effect analysis in order to compare the results of a Bayesian propensity score analysis to a frequentist propensity score analysis. Because no treatment was applied during the analysis period, it was assumed that there would be no treatment effect, or a crash modification factor equal to 1.0. The Bayesian propensity score matching method nominally outperformed the frequentist propensity score matching method in the largest sample and produced near-identical results in the medium sample, but neither method closely approximated the assumed, true crash modification factor in the small sample analysis. A simulation study is recommended to further study the effects of sample size and confounding factors when comparing the Bayesian and frequentist propensity score matching methods.

Does space influence on the frequency and severity of the distraction-affected vehicle crashes? An empirical evidence from the Central Ohio

This study investigates spatial dependencies between frequency and within severity of vehicle crashes caused by distracted driving, along with the role of the built and socio-demographic environments in the Columbus Metropolitan Area, Ohio. We adopt a full Bayesian hierarchical framework with Multivariate Conditional Autoregressive Priors to account for the complex spatial correlation structure as well as the unobserved heterogeneity. Using aggregated crash count data (Property Damage Only and Bodily Injuries) for the 414 census tracts, the analysis outcomes reveal that census tracts providing more jobs and having a higher proportion of commercial land use would have higher likelihood of relative crash risks in both severity levels. Inclusion of correlation structure between frequency as well as within crash-severity-level has proven a significant increase on the performance of the model, verifying influences of space on the frequency and severity of distraction-affected vehicle crashes. In addition, this research presents areas of higher relative risks (spatial clusters) that have 1.5 times elevated risk of collision than other census tracts. The identification of areas of excessive risks informs us to devise policies to mitigate negative consequences of distraction-affected crashes.

The role of striking and struck vehicles in side crashes between vehicles: Bayesian bivariate probit analysis in China

OBJECTIVE

Side crashes between vehicles which usually lead to high casualties and property loss, rank first among total crashes in China. This paper aims to identify the factors associated with injury severity of side crashes at intersections and to provide suggestions for developing countermeasures to mitigate the levels of injuries.

METHOD

In order to investigate the role of striking and struck vehicles in side crashes simultaneously, bivariate probit model was proposed and Bayesian approach was employed to evaluate the model, compared to the corresponding univariate probit model.

DATA

Crash data from Beijing, China for the period 2009-2012 were used to carry out the statistical analysis. Based on the investigation with vehicles and data analysis on events, 130 intersection side crash cases were selected to form a specific dataset. Then, the influence of human, vehicles, roadway and environmental variables on crash severity was examined by means of bivariate probit regression within Bayesian framework.

RESULTS

The effects of the factors on striking vehicle drivers and struck vehicle drivers were considered separately and simultaneously to find more targeted conclusions. The statistical analysis revealed vehicle type, lane number, no non-motorized lane and speeding have the corresponding influence on the injury severity of striking vehicles, while time of day and vehicle type of struck vehicles increased the likelihood of being injured.

CONCLUSIONS

From the results it can be concluded that there indeed exists correlation between striking and struck vehicles in side crashes, although the correlation is not so strong. Importantly, Bayesian bivariate probit model can address the role of striking and struck vehicles in side crashes simultaneously and can accommodate the correlation clearly, which extends the range of univariate probit analysis. The general and empirical countermeasures are presented to improve the safety at intersections.

Macroscopic road safety impacts of public transport: A case study of Melbourne, Australia

Mode shift from private vehicle to public transport is often considered as a potential means of improving road safety, given public transport's lower fatality rates. However, little research has examined how public transport travel contributes to road safety at a macroscopic level. Further, there is a limited understanding of the individual effects of different public transport modes. This paper explores the effects of commuting by public transport on road safety at a macroscopic level, using Melbourne as a case study. A random effect negative binomial (RENB) and a conditional autoregressive (CAR) model are adopted to explore links between total and severe crash data to commuting mode shares and a range of other zonal explanatory factors. Overall, results show the great potential of public transport as a road safety solution. It is evident that mode shift from private vehicle to public transport (i.e. train, tram, and bus), for commuting would reduce not only total crashes, but also severe crashes. Modelling also demonstrated that CAR models outperform RENB models. In addition, results highlight safety issues related to commuting by motorbike and active transport. Effects of sociodemographic, transport network, and land use factors on crashes at the macroscopic level are also discussed.

Mapping the knowledge domain of road safety studies: A scientometric analysis

As a way of obtaining a visual expression of knowledge, mapping knowledge domain (MKD) provides a vision-based analytic approach to scientometric analysis which can be used to reveal an academic community, the structure of its networks, and the dynamic development of a discipline. This study, based on the Science Citation Index Expanded (SCIE) and Social Sciences Citation Index (SSCI) articles on road safety, employs the bibliometric tools VOSviewer and CitNetExplorer to create maps of author co-citation, document co-citation, citation networks, analyze the core authors and classic documents supporting road safety studies and show the citation context and development of such studies. It shows that road safety studies clustered mainly into four groups, whose we will refer to as "effects of driving psychology and behavior on road safety", "causation, frequency and injury severity analysis of road crashes", "epidemiology, assessment and prevention of road traffic injury", and "effects of driver risk factors on driver performance and road safety", respectively. Through our analysis, the core publications and their citation relationships were quickly located and explored, and "crash frequency modeling analysis" has been identified to be the core research topic in road safety studies, with spatial statistical analysis technique emerging as a frontier of this topic.

A mixed methods investigation of bicycle exposure in crash rates

Crash rates are an essential tool enabling researchers and practitioners to assess whether a location is truly more dangerous, or simply serves a higher volume of vehicles. Unfortunately, this simple crash rate is far more difficult to calculate for bicycles due to data challenges and the fact that they are uniquely exposed to both bicycle and automobile volumes on shared roadways. Bicycle count data, though increasingly more available, still represents a fraction of the available count data for automobiles. Further compounding on this, bicycle demand estimation methods often require more data than automobiles to account for the high variability that bicycle demand is subject to. This paper uses a combination of mixed methods to overcome these challenges and to perform an investigation of crash rates and exposure to different traffic volumes.

Incorporating behavioral variables into crash count prediction by severity: A multivariate multiple risk source approach

The frequency and severity of traffic crashes have commonly been used as indicators of crash risk on transport networks. Comprehensive modeling of crash risk should account for both frequency and injury severity-capturing both the extent and intensity of transport risk for designing effective safety improvement programs. Previous research has revealed that crashes are correlated across severity categories because of the combined influence of risk factors, observed or unobserved. Moreover, crashes are the outcomes of a multitude of factors related to roadway design, traffic operations, pavement conditions, driver behavior, human factors, and environmental characteristics, or in more general terms: factors reflect both engineering and non-engineering risk sources. Perhaps not surprisingly, engineering risk sources have dominated the list of variables in the mainstream modeling of crashes whereas non-engineering sources, in particular, behavioral factors, are crucially omitted. It is plausible to assume that crash contributing factors from the same risk source affect crashes in a similar manner, but their influences vary across different risk sources. Conventional crash frequency modeling hypothesizes that the total crash count at any roadway site is well-approximated by a single risk source to which several explanatory variables contribute collaboratively. The conventional formulation is not capable of accounting for variations between risk sources; therefore, is unable to discriminate distinct impacts between engineering variables and non-engineering variables. To address this shortcoming, this study contributes to the development of multivariate multiple risk source regression, a robust modeling technique to model crash frequency and severity simultaneously. The multivariate multiple risk source regression method applied in this study can effectively capture the correlation between severity levels of crash counts while identifyinging the varying effects of crash contributing factors originated from distinct sources. Using crashes on Wisconsin rural two-lane highways, two risk sources - engineering and behavioral - were employed to develop proposed models. The modeling results were compared with a single equation negative binomial (NB) model, and a univariate multiple risk source model. The results show that the multivariate multiple risk source model significantly outperforms the other models in terms of statistical fit across several measures. The study demonstrates a unique approach to explicitly incorporating behavioral factors into crash prediction models while taking crash severity into consideration. More importantly, the parameter estimates provide more insight into the distinct sources of crash risk, which can be used to further inform safety practitioners and guide roadway improvement programs.

Effects of globally obtained informative priors on bayesian safety performance functions developed for Australian crash data

The precision and bias of Safety Performance Functions (SPFs) heavily rely on the data upon which they are estimated. When local (spatially and temporally representative) data are not sufficiently available, the estimated parameters in SPFs are likely to be biased and inefficient. Estimating SPFs using Bayesian inference may moderate the effects of local data insufficiency in that local data can be combined with prior information obtained from other parts of the world to incorporate additional evidence into the SPFs. In past applications of Bayesian models, non-informative priors have routinely been used because incorporating prior information in SPFs is not straightforward. The previous few attempts to employ informative priors in estimating SPFs are mostly based on local prior knowledge and assuming normally distributed priors. Moreover, the unobserved heterogeneity in local data has not been taken into account. As such, the effects of globally derived informative priors on the precision and bias of locally developed SPFs are essentially unknown. This study aims to examine the effects of globally informative priors and their distribution types on the precision and bias of SPFs developed for Australian crash data. To formulate and develop global informative priors, the means and variances of parameter estimates from previous research were critically reviewed. Informative priors were generated using three methods: 1) distribution fitting, 2) endogenous specification of dispersion parameters, and 3) hypothetically increasing the strength of priors obtained from distribution fitting. In so doing, the mean effects of crash contributing factors across the world are significantly different than those same effects in Australia. A total of 25 Bayesian Random Parameters Negative Binomial SPFs were estimated for different types of informative priors across five sample sizes. The means and standard deviations of posterior parameter estimates as well as SPFs goodness of fit were compared between the models across different sample sizes. Globally informative prior for the dispersion parameter substantially increases the precision of a local estimate, even when the variance of local data likelihood is small. In comparison with the conventional use of Normal distribution, Logistic, Weibull and Lognormal distributions yield more accurate parameter estimates for average annual daily traffic, segment length and number of lanes, particularly when sample size is relatively small.

Safety sensitivity to roadway characteristics: A comparison across highway classes

This paper examined the accident risk factors associated with highway traffic and roadway design, for each of three highway classes in the United States using a bivariate modeling framework involving two levels of accident severity. With regard to the highest class (Interstates), the results suggest that, compared to no-casualty accidents, casualty accidents are more sensitive to traffic volume and average vertical grade, but less sensitive to the inside shoulder width and the median width. For US Roads, it was determined that, compared to no-casualty accidents, casualty accidents are more sensitive to traffic volume, outside shoulder width, pavement condition, and median width but less sensitive to the average vertical grade. For the relatively lowest-class roads (State Roads), it was determined that, compared to no-casualty accidents, casualty accidents are more sensitive to the traffic volume, lane width, outside shoulder width, and pavement condition. Compared to the relatively lower-class highways, accidents at higher-class highways are more sensitive to: changes in traffic volume, average vertical grade, median width, inside shoulder width, and the pavement condition (no-casualty accidents only); but less sensitive to changes in lane width, pavement condition (casualty accidents only), and the outside shoulder width. This variation in sensitivity across the different road classes could be attributed to the differences in road geometry standards across the road classes, as the results seem to support the hypothesis that these standards strongly influence accident occurrence. It is hoped that the developed bivariate negative binomial models can help highway engineers to evaluate their current design standards and policy, and to assess the safety consequences of changes in these standards in each road class.

Crash injury severity analysis using a two-layer Stacking framework

Crash injury severity analysis is useful for traffic management agency to further understand severity of crashes. A two-layer Stacking framework is proposed in this study to predict the crash injury severity: The fist layer integrates advantages of three base classification methods: RF (Random Forests), AdaBoost (Adaptive Boosting), and GBDT (Gradient Boosting Decision Tree); the second layer completes classification of crash injury severity based on a Logistic Regression model. A total of 5538 crashes were recorded at 326 freeway diverge areas. In the model calibration, several parameters including the number of trees in three base classification methods, learning rate, and regularization coefficient are optimized via a systematic grid search approach. In the model validation, the performance of the Stacking model is compared with several traditional models including the Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and Random Forests (RF) in the multi classification experiments. The prediction results show that Stacking model achieves superior performance evaluated by two indicators: accuracy and recall. Furthermore, all the factors used in severity prediction are classified into different categories according to their influence on the results, and sensitivity analysis of several significant factors is finally implemented to explore the impact of their value variation on the prediction accuracy.

Joint Modeling of Mixed Plasmodium Species Infections Using a Bivariate Poisson Lognormal Model

Infectious diseases often present as coinfections that may affect each other in positive or negative ways. Understanding the relationship between two coinfecting pathogens is thus important to understand the risk of infection and burden of disease caused by each pathogen. Although coinfections with Plasmodium falciparum and Plasmodium vivax are very common outside Africa, it is yet unclear whether infections by the two parasite species are positively associated or if infection by one parasite suppresses the other. In this study, we use bivariate Poisson lognormal models (BPLM) to estimate covariate-adjusted associations between the incidence of infections (as measured by the force of blood-stage infections, _molFOI) and clinical episodes caused by both P. falciparum and P. vivax in a cohort of Papua New Guinean children. A BPLM permits estimation of either positive or negative correlation, unlike most other multivariate Poisson models. Our results demonstrated a moderately positive association between P. falciparum and P. vivax infection rates, arguing against the hypothesis that P. vivax infections protect against P. falciparum infections. Our findings also suggest that the BPLM is only useful for counts with suitably large means and overdispersion.

A Bayesian multivariate hierarchical spatial joint model for predicting crash counts by crash type at intersections and segments along corridors

The safety and operational improvements of corridors have been the focus of many studies since they carry most traffic on the road network. Estimating a crash prediction model for total crash counts identifies the crash risk factors that are associated with crash counts at a specific type of road entity. However, this may not reveal useful information to detect the road problems and implement effective countermeasures. Therefore, investigating the contributing factors for crash counts by different types is of great importance. This study aims to provide a good understanding of the contributing factors to crash counts by different types at intersections and roadway segments along corridors. Data from 255 signalized intersections and 220 roadway segments along 20 corridors have been used for this study. The investigated crash types include same direction, angle and turning, opposite direction, non-motorized, single vehicle, and other multi-vehicle crashes. Two models have been estimated, which are multivariate hierarchical Poisson-lognormal (HPLN) spatial joint model and univariate HPLN spatial joint model. The significant variables include exposure measures and some geometric design variables at intersection, roadway segment, and corridor levels. The results revealed that the multivariate HPLN spatial joint model outperforms the univariate HPLN spatial joint model. Also, the correlations among crash counts of most types exist at individual road entity and between adjacent entities. Additionally, the significant explanatory variables are different across crash types, and the magnitude of the parameter estimates for the same independent variable is different across crash types. The results emphasize the need for estimating crash counts by type in a multivariate form to better detect the problems and provide appropriate countermeasures.

Predicting crash frequency for multi-vehicle collision types using multivariate Poisson-lognormal spatial model: A comparative analysis

According to crash configuration and pre-crash conditions, traffic crashes are classified into different collision types. Based on the literature, multi-vehicle crashes, such as head-on, rear-end, and angle crashes, are more frequent than single-vehicle crashes, and most often result in serious consequences. From a methodological point of view, the majority of prior studies focused on multivehicle collisions have employed univariate count models to estimate crash counts separately by collision type. However, univariate models fail to account for correlations which may exist between different collision types. Among others, multivariate Poisson lognormal (MVPLN) model with spatial correlation is a promising multivariate specification because it not only allows for unobserved heterogeneity (extra-Poisson variation) and dependencies between collision types, but also spatial correlation between adjacent sites. However, the MVPLN spatial model has rarely been applied in previous research for simultaneously modelling crash counts by collision type. Therefore, this study aims at utilizing a MVPLN spatial model to estimate crash counts for four different multi-vehicle collision types, including head-on, rear-end, angle, and sideswipe collisions. To investigate the performance of the MVPLN spatial model, a two-stage model and a univariate Poisson lognormal model (UNPLN) spatial model were also developed in this study. Detailed information on roadway characteristics, traffic volume, and crash history were collected on 407 homogeneous segments from Malaysian federal roads. The results indicate that the MVPLN spatial model outperforms the other comparing models in terms of goodness-of-fit measures. The results also show that the inclusion of spatial heterogeneity in the multivariate model significantly improves the model fit, as indicated by the Deviance Information Criterion (DIC). The correlation between crash types is high and positive, implying that the occurrence of a specific collision type is highly associated with the occurrence of other crash types on the same road segment. These results support the utilization of the MVPLN spatial model when predicting crash counts by collision manner. In terms of contributing factors, the results show that distinct crash types are attributed to different subsets of explanatory variables.

Bayesian Poisson hierarchical models for crash data analysis: Investigating the impact of model choice on site-specific predictions

The Poisson-gamma (PG) and Poisson-lognormal (PLN) regression models are among the most popular means for motor vehicle crash data analysis. Both models belong to the Poisson-hierarchical family of models. While numerous studies have compared the overall performance of alternative Bayesian Poisson-hierarchical models, little research has addressed the impact of model choice on the expected crash frequency prediction at individual sites. This paper sought to examine whether there are any trends among candidate models predictions e.g., that an alternative model's prediction for sites with certain conditions tends to be higher (or lower) than that from another model. In addition to the PG and PLN models, this research formulated a new member of the Poisson-hierarchical family of models: the Poisson-inverse gamma (PIGam). Three field datasets (from Texas, Michigan and Indiana) covering a wide range of over-dispersion characteristics were selected for analysis. This study demonstrated that the model choice can be critical when the calibrated models are used for prediction at new sites, especially when the data are highly over-dispersed. For all three datasets, the PIGam model would predict higher expected crash frequencies than would the PLN and PG models, in order, indicating a clear link between the models predictions and the shape of their mixing distributions (i.e., gamma, lognormal, and inverse gamma, respectively). The thicker tail of the PIGam and PLN models (in order) may provide an advantage when the data are highly over-dispersed. The analysis results also illustrated a major deficiency of the Deviance Information Criterion (DIC) in comparing the goodness-of-fit of hierarchical models; models with drastically different set of coefficients (and thus predictions for new sites) may yield similar DIC values, because the DIC only accounts for the parameters in the lowest (observation) level of the hierarchy and ignores the higher levels (regression coefficients).

Predicting motorcycle crash injury severity using weather data and alternative Bayesian multivariate crash frequency models

Motorcycle crashes constitute a very high proportion of the overall motor vehicle fatalities in the United States, and many studies have examined the influential factors under various conditions. However, research on the impact of weather conditions on the motorcycle crash severity is not well documented. In this study, we examined the impact of weather conditions on motorcycle crash injuries at four different severity levels using San Francisco motorcycle crash injury data. Five models were developed using Full Bayesian formulation accounting for different correlations commonly seen in crash data and then compared for fitness and performance. Results indicate that the models with serial and severity variations of parameters had superior fit, and the capability of accurate crash prediction. The inferences from the parameter estimates from the five models were: an increase in the air temperature reduced the possibility of a fatal crash but had a reverse impact on crashes of other severity levels; humidity in air was not observed to have a predictable or strong impact on crashes; the occurrence of rainfall decreased the possibility of crashes for all severity levels. Transportation agencies might benefit from the research results to improve road safety by providing motorcyclists with information regarding the risk of certain crash severity levels for special weather conditions.