Search

How a household’s travel behavior is influenced by its socioeconomic and land use factors has been a subject of interest for the development of travel demand forecasting models. This study investigates the relative importance of these factors based on the number of household daily trips and vehicle miles traveled (VMT). The travel data used in the study come from the 1994 Portland Activity-Based Travel Survey. In addition to income, vehicle ownership, and household size, other significant factors in household travel have been identified, such as the presence of car phones, dwelling type, home ownership, and even the length of resident’s time in the current home. Most important, this study has qualitatively revealed that land use makes a big difference in household VMT, whereas its impact on the number of daily trips is rather limited. After controlling for the land use variables, such as density and land development balance, it appears that there is little difference in household income distribution among three different land use areas. The household life stage/lifestyle appears to be more relevant to the residence location. And the land use development of the residence location imposes the greatest impact on the household daily VMT. The results from this study provide some empirical evidence to the development of travel forecasting models. Especially by examining the relationship between land use and household travel, the results shed light on how to incorporate land use factors into comprehensive travel demand models that can be used by policy makers in evaluation of alternative land use policies. This study serves as a step toward more comprehensive studies on transportation and land use. The results presented represent a preliminary analysis of an extensive data set; considerable additional analysis is already in process.

In order to find appropriate safety treatments for pedestrian crossing locations in rural areas of China, a hybrid energy absorbing reusable refuge island was designed and evaluated using finite element crash simulation modeling. This new type of refuge island contained reusable thermoplastic crash cushions and a series of self-restorative bollards for shielding pedestrians. It possessed excellent energy dissipation properties. Computer analysis models of car, crash cushion and bollard were developed. The refuge island was successfully evaluated by mid-size passenger car crash simulations using LS-DYNA. No detached elements, fragments, or other debris are present to penetrate the occupant compartment or present a hazard to pedestrians in the refuge island area. Since it has durability and economical efficiency, after passing an actual crash test the proposed reusable refuge island can be installed in pedestrian crossing locations in rural China such as midblock or at intersections.

Xi-Han Freeway is a unique freeway passing through a mountainous region with very challenging topography and complex climatic conditions. This freeway is built with many bridges and tunnels that greatly complicated the alignment design. Since its opening in 2007, the safety has become a serious concern due to the high crash risk. This paper presents the results of a crash analysis and consequent proposal on the crash countermeasures for Xi-Han Freeway are presented. This research provides evidence on how to improve safety of freeways in mountainous regions in China.

This paper studies a frequent violation at multi-phase signal intersection of Beijing, that large number of pedestrians twice crossing street in the left-turn phase. Based on a large number of measured data, the influence of this violation on intersection safety is analyzed by using the theory of traffic conflict. To solve the violation, some strategy and methods have also been summarized. As an important link in City Road system and a crucial section of the whole road net, the intersections in the city act as the nodes connecting the crossing roads and control the vehicle volume. Due to the complexity of traffic participants and the high concentration of traffic flow, traffic accidents are very liable to occur in the crossings. According to the traffic accident statistics in China (2008), there are 46148 traffic accidents in crossings, taking account of 17.40% of the total number of the traffic accidents and leading to 9549 death. (Ministry of Public Security, 2009) Therefore the studies on the influence factors of crossings safety have been considered as an urgent need. Multi-phase signal has been adopted in increasing amount as an effective method to improve the traffic safety. In this system, the left-turn phase is put forward to separate the straight flow and left-turn flow to different time sections, thus to decrease the traffic confliction points. However, the implementation of left-turn phrase will to some extent extend the waiting time for the pedestrians passing through the streets. The pedestrians are likely to break the traffic rules and cross the roads regardless of the traffic signal if the waiting time is too long or the waiting crowd has reached saturation. Normally they

LOSS (Level of Service of Safety) is used to weigh the quality of safe operation that roads provide to the drivers and other traffic participants. Reasonable speed limit not only controls the speed of vehicles in appropriate range on the road, but also guarantees the traffic safety of the road. Crash rate was selected as a quantitative indicator, hierarchical standard of LOSS for freeway and arterial highway was studied, and then the LOSSs of freeway and arterial highway in China were divided into 4 levels. In virtue of the probability statistics, robust regression and on the basis of accident data, speed limit and geometric factors the accident prediction models were established. Based on the acceptable LOSS the method of setting speed limits about cars and trucks respectively was formed. The results would help traffic engineers in Chinese highway management departments choose right speed limits for freeway and arterial highway.

In recent years, China's road speeding accidents have increased each year. As a consequence, the property damage caused by the accidents is increasing as well. Since the automatic enforcement requires less police but have good effect of speed limit and have a significant superiority in road traffic management. As a result, more and more cities in China use automatic enforcement in speed limit management. The paper analyzes the speed limit effects of two different law enforcement equipments namely the camera and the radar separately. The research ultimately concluded that the radar has a certain speed limit effect but the speed limit durability is poor. In addition, the study examines that the camera's effects of speed limit are the most effective as they not only can bring the speed down efficiently but also have good continuity of speed limit effects.

The paper emphasizes that posted speed limit does not directly have impact on accidents. On the contrary, it influences traffic safety through operating speed. Therefore, it's essential to explore the relationship between them. In this paper, the conditions of the same posted speed limit were analyzed. In addition, some comparisons between 1st-class highways and 2nd-class highways about operating speed were made. It can be found that posted speed limit significantly impact on operating speed. The operating speed is usually larger than the posted speed limit. With the change of the posted speed limit, the operating speed reduces or increases accordingly.

As a dynamic system, the road traffic system is made of people, vehicles, road and traffic environment and any factor's change will affect system. The article focuses on Lian Huo Road of Xinjiang and Qing Lian Road of Guangdong of first class highway and does a comparative analysis to road traffic accidents features from the angle of the accident form, the cause of the accident, the accident vehicle types. Finally, it gives the reasons of accident difference.

This paper studied the relationship between speed differences and crash rates using nine of China's freeway speed and accident data. Research shows that the accident rate has correlations with the dispersion of speed. According to the accident rate and speed scatter Distribution, three kinds of models will be carried out, analyzing the significant level of F, as well as R2 amendment. The authors arrived at the index distribution model of accident rate and speed standard deviation.

Large speed gaps may increase risks between adjacent speed zones. Therefore, a speed transition zone is designed to provide a smooth change between two highway segments with different speed limits. The purpose of this study is to establish a procedure for transitional speed zone design on two-lane roads by using drivers’ behavioral statistics. In order to evaluate the effect of the speed limit zone on drivers’ deceleration behaviors when passing different speed zones, two factors were considered in this study: existence of work zones and horizon curves. The speed gaps in this experiment are 50 km/h in work zone areas and 20 km/h respectively. By using randomly selected drivers, the study measured drivers’ actions in a real vehicle under the simulated environment traveling between speed zones at a 0.03 second intervals. Several different measures of effectiveness were used to compare the characteristics of the speed distributions, including average speed, 85th percentile speed and pace speed. Results show that there is a significant difference in speed choice for deceleration between two scenarios due to speed reduction. The relationship between speed limit reduction and deceleration length is described by a linear model. The length of the deceleration section is estimated by the model. Results show that the deceleration section is positively correlated to speed reduction. The modeling process gives detailed guidance for the design of a transitional speed zone.

Countdown signal can be used to remind drivers when the colors of signal change and help them choose appropriate driving behavior to go through an intersection between stoppings and crossings. It is a method to reduce complexity of judgments for drivers when the colors of a signal change. In China, the study on the effects of countdown signal at intersections on drivers’ violating behavior is few. From the results of the investigative questionnaire, more than 85% of drivers and pedestrians preferred countdown signal to no-countdown signal. More than 85% of drivers and pedestrians thought the intersection with countdown signal was safer than the intersection with no-countdown signal. The paper will be researched on an intersection with four legs in Beijing fangzhuang district in the virtue of video recorders. It analyzed the drivers’ behavior during seven days before and after installing the countdown signal respectively, which was digit-display countdown timing and showed the whole green and red time. The findings indicated that traffic volumes were quite similar before and after installing the countdown signal, however, the drivers’ behavior of yellow-crossing and red-running decreased significantly after installing the countdown signal.

Using design speed as a primary consideration for selecting the speed limit of a freeway has been a common practice since the opening of the first freeway in China about twenty years ago. This practice has been widely questioned and challenged in recent years by the public, freeway operators, and law enforcement. Speed limits solely based on the location specific design speed in many newly completed freeways in the country have been under intensive public scrutiny, particularly at locations where the operating speeds are much higher or lower than the speed limits. One key consideration in establishing speed limit is the operating speed that closely relates to driver behavior, vehicles' mechanic properties, and the design speed. Driver behavior varies greatly by factors including cultural background and stage of economic development. Undoubtedly different social, economic, and cultural environments contribute to significant variation in driver behavior. The methods used by developed countries in speed limit selection may not be suitable, or at least not entirely applicable, to situations in developing countries. Thus, as part of a project sponsored by the Chinese Ministry of Communication, the goal of this study is to investigate the relationship between speed limit and operating speed in different freeway environments. The principal findings from the study are: (a) operating speed is only loosely associated with speed limit, (b) for a given speed limit, the average speed varies greatly depending on the characteristics of the location, (c) standard deviation of operating speed distribution on freeways in China is generally much bigger than on a typical freeway in developed countries, and (d) there are huge speed gaps between small and large vehicles. The last two findings represent a big safety problem for freeway transportation. The combination of speeding and slow running vehicles on freeways significantly lowers freeway capacity, as well. The unique speed characteristics observed by this study prompts a few suggestions on speed limit and speed management.

The freeways crossing mountainous areas in China are playing a major role in economic development. In the past decade, building freeways in these regions have greatly stimulated economic development in all aspects and will also be a major factor in the areas’ sustainable development for the future. Due to the geometry of highways, freeway accidents have become a serious problem in these mountainous areas. This paper focused on the modeling of freeway safety with the consideration of geometry, traffic flow, and roadside environment. Particularly, the generalized regression model was developed based on the data collected from the mountainous areas.

Controlling speed is very important for roadway safety since speeding increases the severity of crashes. By offering the highest mobility, freeways are more vulnerable to fatalities and crashes involving injury. How to effectively control operating speeds at certain freeway sections is an important topic in China. This paper presents a study on the effectiveness of rumble strips on freeways through a user survey and field observation. The main results indicate that drivers’ view of the effectiveness of rumble strips on freeways is inconsistent in different regions. By analyzing speed before and after rumble strips, this paper tries to estimate the impact of this speed control device on speed reduction.

The effect of speed limit enforcement ultimately depends on the presence of police and other speed control technology. If the speed limit for a section of the highway is perceived to be low by the majority of motorists, there would be a high proportion of speeding vehicles. Enforcing the speed limit law at such locations demands tremendous police resources. This would increase the cost of enforcement. If the speed limits at such locations are not enforced due to a lack of police manpower, the crash risk could be much higher. This paper divides the enforcement cost into several components, then analyzes the speed limit effects of automatic speeding enforcement and artificial speeding enforcement through the data from the survey. It ultimately arrives at the conclusion that automatic speeding enforcement has a much better effect on maintaining speed limit than artificial speeding enforcement. Further it is proved that the camera is more effective than the radar.

This study analyzed the relationships between alignment elements and traffic accidents, traffic flow characteristics and traffic accidents, and environmental features and traffic accidents, which were based on the presumption that drivers on the freeway had better conditions for steering and had experience driving. The findings from the freeway Jing Jintang in plain terrain is that the ideal alignment design is not a main factor causing traffic accidents. There are strong and obvious correlations between traffic flow characteristics and traffic accidents and environmental features and traffic accidents. By means of nonlinear regression, the crash rates prediction models were constructed, the dependent variables are crash rates including three types which are: property damage only accident rate, casualty accident rate and the total accident rate. The independent variables are the characteristics of traffic flow and the environment. The three models can be used as management tools for traffic engineers to measure the safety of freeways.

Roadway rumble strips are used to reduce driving comfort and make drivers decelerate. While vehicle suspension systems are designed for passengers’ comfort by absorbing vibrations caused by bumping roadway surface, roadway rumble strips are implemented to alert motorists to reduce speed. An efficient and safe roadway rumble strips design depends on the understanding of the vehicles’ suspension system. Newer marked vehicles always have better suspension system that can absorb higher vibrations. This paper investigates the relationship between vehicle suspension system and roadway rumble strips design through TruckSim, a computer simulation model for trucks. The study analyzes the various shock-absorbing effect of current popular vehicle suspension systems on the roadway rumble strips designs in order to evaluate roadway rumble strips effectiveness in speed reduction. BACKGROUND There were 265,204 auto accidents in China in 2008. The direct financial cost of these crashes was more than 1.01 billion Yuan. 73,484 people were killed and 304,919 people injured. Speeding-related crashes account for over 10.17% of these auto accidents. 14.40% of killed people, 9.44% of injured people and 10.59% of the direct financial cost of these crashes (M.P.S., 2008). Speeding is thus a danger to all road users. When researchers do their best for the improvement of the road safety, many new methods and facilities are raised for application. Roadway rumble strips are a speed limit feature for road safety and have an extensive application on the freeway with sharp curves or long steep slopes. This article analyzes accelerations of seat surface when trucks with different suspension systems pass over different roadway rumble strips.

On the basis of exploring the significance of research on the vehicular operating speeds on long tangent expressway sections, this study collected the continuous and undisturbed operating speed data of passenger cars on long tangent sections by advanced (vehicle-based) global positioning system (GPS) devices and analyzed the vehicular operation speeds on the sampled long tangent expressway sections. Then, in consideration of the variations of vehicular operating speed on long tangent sections and drivers’ characteristics on the sections such as tendency toward speeding, lagging responses, etc, a model of continuous vehicular operating speeds on long tangent sections was developed in the form of a second order differential equation.

Objective To study the clinical characteristics of patients with severe ocular chemical injury in Shanghai and to determine their relationship with visual outcome. Design Retrospective case series. Participants A total of 79 525 in-patients at Shanghai Eye, Ear, Nose, and Throat Hospital between 1998 and 2008. Methods Medical records of severe ocular chemical injuries were reviewed retrospectively. Patients' age, gender, occupation, location where injury occurred, the nature of chemical agent, complication, and visual acuity at final follow-up were described. The relationship between visual impairment and clinical characteristics was analyzed. Main Outcome Measures Estimated prevalence rate, demographics of patients, nature of injury, prognosis, and factors associated with visual impairment. Results The estimated prevalence rate in Shanghai of severe ocular chemical injury was 1.58 per 100 000. One hundred ninety cases with 239 eyes were identified for analyzing the clinical characteristics. The average age of all subjects was 35.3±14.8 years with a male:female ratio of 6:1. Factory and construction worker (n = 141; 74.2% of total cases) were the most common occupations. Most of the accidents occurred at workplace (n = 144; 74.8%); the majority of injuries were caused by alkali agents (n = 129; 67.9%). Complications were found in 222 eyes (92.9%). A visual acuity of ≥6/60 was achieved only in 5 eyes (2.1%). In multivariate logistic regression analysis, being visually impaired was significantly associated with the patients' complication (P = 0.021). Conclusions The prevalence of severe ocular chemical injury in Shanghai is low. Most subjects needed surgery to restore visual function. Successful management provides a good prognosis for most patients. Financial Disclosure(s) The authors have no proprietary or commercial interest in any of the materials discussed in this article.

In order to improve the safety level of mountainous two-lane highway, this paper investigated the relationship between highway geometric features and rear-end crash incidence. By using negative binomial generalized models and separating the 139 kilometers highway segment into 94 successive vertical slope units, the statistical software Stata9.0 was used to evaluate the effects of eight (8) variables which were based on roadway geometric characteristics on the incidence of rear-end crashes occurred from 2003 to 2005 on mountainous two-lane highway in Gansu Province. Unrelated geometric variables were dropped one by one by using step regressing method. Finally, the variables found to influence the incidence of rear-end crashes significantly was accumulated vertical slope length. The regression analysis results suggest that there are strong positive relationships between the incidence of rear-end crashes and accumulated vertical slope length. So it is wise to avoid too long successive down slope when designers are engaged in fresh highway designs on considering safety effect.

Speeding is one of the most prevalent factors contributing to traffic crashes. Speed limit is one of the strategies to enforce traffic safety by controlling drivers' choices. This paper discusses the rationality of speed limit on Bosai highway in Xinjiang Province. In order to evaluate the rationality of speed limit, three study sites were posted in the vicinity of a speed limit sign. Speed distributions inside and outside the speed limit zone, crash records and drivers' compliance were examined. Significance of speed differences was tested by independent t test. Results show that 100km/h speed limit for passenger cars is within drivers' expectation and 80km/h speed limit for commercial vehicles is unreasonably high. As to the safety impacts, there is no evidence supporting the relationship between crashes and speed limit due to the limited data. The checking process has a practical aspect for speed determination and optimal use of limited road resources.

Mixed traffic is a significant feature of Chinese traffic flow on urban street network, which is also a major cause of traffic congestion and frequent traffic accidents. In sections where motor vehicles and non-motor vehicles moving in same direction without separation, they would interfere with each other. This interference has serious impact on the capacity of sections, and simultaneously increases the accident risk. This paper analyzed the data through the method of probability theory and statistics， and got the result that “the number of non-motor vehicles and the lateral distant between motor vehicles and non-motor vehicles are both interference factors aroused by non-motor vehicles”. Finally, non-motor vehicles' disturbance model to the motor vehicles were set up based on data analysis and proved to be correctly. The research provided a theoretical and basis to the traffic safety management under the mixed

In the recent years, in china, speeding is one of the most serious road traffic violations and is one of the main reasons that cause road traffic accidents. In 2007, the road traffic accident fatalities caused by speeding account for 14.06% of the total, ahead of the main reasons for the accident, so the treatment of speeding is the main task of the traffic control department. This article, from the point of view of expected speed of driver, studies the mechanism of its formation, and establishes the relationship model between speeding rate and traffic volume through the measured data in the field. The model can help traffic control department to identify road sections and time sections in which speeding happens very often. That will allow police to focus on control and improve law enforcement efficiency and reduce the

This paper presents a study on the development of safety performance function for freeways. Applying well-established statistical methods, we evaluated all variables that may affect freeway safety and selected the most signifi cant ones in the model. A variable analysis unit was utilized in this study to overcome the diffi culties in obtaining accurate crash and highway attribute data, as well as to improve the modelling quality. The results of this study provide much needed tools for freeway safety analysis.

Highway Safety Management Process will be introduced in the first edition of Highway Safety Manual (HSM). This systematic process consists of several tasks starting with network screening. The purpose of network screening is to identify the locations with high potential in crash reduction through highway improvement projects. Nine screening methods are going to be presented in the network screening chapter of HSM and each of them has unique strength and weakness. It is interesting to see how each of these methods works on a large highway network from a real world study in addition to the application examples provided in the chapter.

While investigating Jingjintang Expressway's traffic accidents, it is clear that, crash frequency and rates at interchange areas re more severe than at other locations. To further explore the relationship between crash rates and characteristics of freeway geometric design features, this study analyzed the existing safety problems at Jingjintang Expressway’s interchanges. Particularly the authors examined crash characteristics at ramps including length of acceleration lanes and deceleration lanes, ramp geometric design, traffic control devices at ramps and locations of toll plazas. The driver behavior and performance overloaded trucks on ramps were also studied. The results of the study have clearly shown that it is important to have a uniform traffic information system and a consistent traffic control system. Most importantly, the study has concluded that the length requirements in the authors' current design specification for ramp acceleration and decoration lanes are not sufficient for safety, particularly for large vehicles. A set of recommendations is made as a result of this study.

There are about 1,520 miles of multiple-lane (excluding freeway) highways in Louisiana that amounts to 9% of all highways on the Louisiana Department of Transportation and Development (LaDOTD) roadway system. However close to 50% of total crashes and 22% of total fatal crashes occur on multiple-lane highways annually. Reducing number of crashes on multiple-lane highways is crucial for LaDOTD. This paper investigates characteristics of crashes on multiple-lane highways in Louisiana and identifies the top sites for safety improvements by the network screening methods introduced by the on-going Highway Safety Manual projects. Classifying the multiple-lane highways by median (divided and undivided) and area (urban and rural), the results show that urban undivided highway is the most dangerous highway with the highest overall crash rate, and rural divided highways is the most fatal highway with the highest fatality rate in Louisiana. Unlike other types of highways, collisions with other vehicles consist of more than 70% of all crashes. Rear-end crash is the most common type of collision on this type of highways. The results from network screening reveal the characteristics of top ranking sites by four different methods.

The rate of incidents involving commercial vehicles is a particular concern in China, accounting for an estimated 35.8% of all crashes in 2004 and over 30% in 2005. Commercial motor vehicle safety issues in China were studied by collecting data from Jingjintang freeway, which serves as the primary high-speed link between the cities of Beijing and Tianjin, China. For this study, heavy vehicles refer to vehicles with a gross weight of at least 20,000 ponds or vehicles designed to transport at least 40 passengers. This vehicle type is a surrogate for most Commercial Vehicles. Mid-sized vehicles are those the with a gross weight between 10,000 to 20,000 ponds, or vehicles designed to transport 20 to 39 passengers. Light/compact-sized vehicles are those smaller than the mid-size. Commercial vehicles are over-represented in collision involvement, and crashes that involve commercial vehicles have a higher severity level. Data collected from a survey of commercial vehicles and drivers was analyzed for statistical relationships between collision probability and causes related to driver behavior, driver training, and vehicle mechanical condition. Higher crash risk corresponds to lower driver experience, increased driver tendency to load a vehicle in excess of design capacity, operation of older or defective vehicles, and driver tendency to travel at excessive speeds. Based on the known factors influencing commercial vehicle crash probabilities, a number of potential safety countermeasures are suggested for further study in China.

1 Abstract In Chinese highway system, especially within mountainous areas, there arose plenty of excessive long down-hill highway segments. Accident documents from many provinces revealed many of those long down-hill segments burdened substantially with high traffic crash frequency. Preliminary analysis showed that it was truck to dominate the majority of crash involved vehicles in these down-hill segments due to malfunction of braking system. This paper concentrates on the traffic safety performance of down-grade segments of mountainous highways to seek how the traffic and design factors aggregate the risks of vehicle, and most importantly, to glean how the primary index, length of grade, influence the safety performance of road segments. Specially highlighted among this paper's findings is the causation model between length of grade and crash counts under the interaction with other confounding factors such as grade and curvature of horizontal alignments. This outcome would hopefully be employed as the meaningful reference to highway geometry design, especially for the restriction of plausible length of down-hill highway grades.

The roadway section division is the first step to establish accident prediction model. Generally speaking, there are two methods in the roadway section division: One is fixed length method, namely the roadway section is divided into the fixed length, like 0.5 km (mile), 1 km (mile) and so on. The other is variable length method, in which the section division is usually conducted according to the changes of the independent variables, e.g. traffic volume, speed limit and geometric design elements like horizontal curvature, vertical grade, lane numbers, shoulder width, and so on. Regarding the freeway, both two methods have certain deficiencies. This study proposed a new method of freeway section division based on the ordinal clustering method, and the clustering index is the accident frequency per kilometer distributed along the roadway. Through example analysis, we discovered that accident frequency of each segment obtained by this method was obedient to certain probability distribution, which is beneficial to the model establishment, and this method has a good application value.

In 2013, 346 out of 616 fatal crashes in Louisiana were single vehicle crashes with Run-Off-Road (ROR) crashes being the most common type of single vehicle crash. In order to create effective countermeasures for reducing the number of fatal single vehicle ROR crashes, it is important to identify any associated key factors that can quantitatively assess the performance of roads, vehicles and humans. This research uses Multiple Correspondence Analysis (MCA), a multidimensional descriptive data analysis method that associates a combination of factors based on their relative distance in a two dimensional plane, to analyze eight years (2004–2011) of fatal ROR crashes in Louisiana. This method measures important contributing factors and their degree of association. The results revealed that drivers of lightweight trucks, drivers on undivided state highways, male drivers in passenger-vehicles at dawn, older female (65–74) drivers in non-passenger vehicles, older drivers facing hardship to yield in partial access control zones, and drivers with poor reaction time due to impaired driving were closely associated with fatal ROR crashes. Results of the MCA method can help researchers select the most effective crash countermeasures. Further work on the degree of association between the identified crash contributing factors can help safety management systems develop the most efficient crash reduction strategies.

At-fault crash-prone drivers are usually considered as the high risk group for possible future incidents or crashes. In Louisiana, 34% of crashes are repeatedly committed by the at-fault crash-prone drivers who represent only 5% of the total licensed drivers in the state. This research has conducted an exploratory data analysis based on the driver faultiness and proneness. The objective of this study is to develop a crash prediction model to estimate the likelihood of future crashes for the at-fault drivers. The logistic regression method is used by employing eight years' traffic crash data (2004–2011) in Louisiana. Crash predictors such as the driver's crash involvement, crash and road characteristics, human factors, collision type, and environmental factors are considered in the model. The at-fault and not-at-fault status of the crashes are used as the response variable. The developed model has identified a few important variables, and is used to correctly classify at-fault crashes up to 62.40% with a specificity of 77.25%. This model can identify as many as 62.40% of the crash incidence of at-fault drivers in the upcoming year. Traffic agencies can use the model for monitoring the performance of an at-fault crash-prone drivers and making roadway improvements meant to reduce crash proneness. From the findings, it is recommended that crash-prone drivers should be targeted for special safety programs regularly through education and regulations.