Assessment of Crash Occurrence Using Historical Crash Data and a Random Effect Negative Binomial Model: A Case Study for a Rural State

2021 ◽  
pp. 036119812110275
Author(s):  
Karla J Diaz-Corro ◽  
Leyla Coronel Moreno ◽  
Suman Mitra ◽  
Sarah Hernandez
Keyword(s):  
Serial Correlation ◽  
Goodness Of Fit ◽  
Negative Binomial ◽  
Random Effect ◽  
Functional Class ◽  
Average Wind Speed ◽  
Causal Factors ◽  
Crash Data ◽  
Average Precipitation ◽  
Unit Increase

This work identifies factors that influence crash occurrence within a traffic analysis zone (TAZ) by accounting for location-specific effects and serial correlation in longitudinal crash data. This is accomplished by applying a random effect negative binomial (RENB) model. Unlike commonly used count models such as Poisson and negative binomial (NB), RENB accounts for heterogeneity and serial correlation in crash occurrence. An RENB was applied to 15 years of crash data in Arkansas with 1,817 TAZs. Four models were developed for total crashes and by severity (property damage only (PDO), injury, and fatal). RENB-estimated impacts were measured using the incidence rate ratio (IRR). The significant causal factors found to increase in observed crashes include: (i) average precipitation (a one-unit increase in average precipitation results in a 134% increase in total monthly crashes for a TAZ); (ii) average wind speed (16%); (iii) urban designation (7%); (iv) traffic volume (2%); and (v) total roadway mileage (1% for each functional class). Snow depth and days of sunshine were found to decrease the number of accidents by 15% and 2%, respectively. Employment and total population had no impact on crash occurrence. Goodness-of-fit comparisons show that RENB provides the best fit among Poisson and NB formulations. All four model diagnostics confirm the presence of over-dispersion and serial correlation indicating the necessity of RENB model estimation. The main contribution of this work is the identification of crash causal factors at the TAZ level for longitudinal data, which supports data-driven performance measurement requirements of recent federal legislation.

scholarly journals Investigating Pedestrian Injury Crashes on Modern Roundabouts in Addis Ababa, Ethiopia

2015 ◽  
Vol 2512 (1) ◽  
pp. 1-10 ◽  
Author(s):  
Getu Segni Tulu ◽  
M. Mazharul Haque ◽  
Simon Washington ◽  
Mark J. King
Keyword(s):  
Low Income ◽  
Goodness Of Fit ◽  
Negative Binomial ◽  
Addis Ababa ◽  
Random Effect ◽  
Pedestrian Safety ◽  
Fit Statistics ◽  
Traffic Characteristics ◽  
Multiple Observations ◽  
Pedestrian Crashes

Pedestrian crashes represent about 40% of total fatal crashes in low-income developing countries. Although many pedestrian crashes in these countries occur at unsignalized intersections such as roundabouts, studies focusing on this issue are limited. The objective of this study was to develop safety performance functions for pedestrian crashes at modern roundabouts to identify significant roadway geometric, traffic, and land use characteristics related to pedestrian safety. Detailed data, including various forms of exposure, geometric and traffic characteristics, and spatial factors such as proximity to schools and to drinking establishments were collected from a sample of 22 modern roundabouts in Addis Ababa, Ethiopia, representing about 56% of such roundabouts in Addis Ababa. To account for spatial correlation resulting from multiple observations at a roundabout, both the random effect Poisson (REP) and random effect negative binomial (RENB) regression models were estimated. Model goodness-of-fit statistics revealed a marginally superior fit of the REP model to the data compared with the RENB model. Pedestrian crossing volume and the product of traffic volumes along major and minor roads had significant and positive associations with pedestrian crashes at roundabouts. The presence of a public transport (bus or taxi) terminal beside a roundabout was associated with increased pedestrian crashes. Although the maximum gradient of an approach road was negatively associated with pedestrian safety, the provision of a raised median along an approach appeared to increase pedestrian safety at roundabouts. Remedial measures were identified for combating pedestrian safety problems at roundabouts in the context of a developing country.

Examining Safety on Two-Lane and Multilane Highways in Consideration of Access Spacing

2019 ◽  
Vol 2673 (11) ◽  
pp. 388-397
Author(s):  
Raha Hamzeie ◽  
Megat-Usamah Megat-Johari ◽  
Iftin Thompson ◽  
Timothy P. Barrette ◽  
Trevor Kirsch ◽  
...  
Keyword(s):  
Negative Binomial ◽  
Random Effect ◽  
Management Strategies ◽  
Negative Binomial Regression ◽  
Access Point ◽  
Management Policy ◽  
Crash Risk ◽  
Access Management ◽  
Crash Data ◽  
Crash Rates

Access management strategies, such as the introduction of minimum access point spacing criteria and turning movement restrictions, have been shown to be important elements in optimizing the operational and safety performance of roadway segments. The relationship between safety and these types of access policies is a complex issue, and the impacts of such features on traffic crashes is critical to the development of appropriate access management strategies. The purpose of this study was to provide a quantitative evaluation of how crash risk on multilane and two-lane highways varies with respect to access spacing in support of the development of a revised access management policy. Data were obtained for approximately 1,247 and 5,795 mi of segments across multilane and two-lane highways, respectively. Crash data were obtained for a five-year period from 2012 to 2016 and a series of random effect negative binomial regression models were estimated for each facility to examine the association between crash frequency, access point spacing, and traffic volume. For both facility types, crashes were found to increase consistently as the average spacing of access points along road segments decreased. Crash rates were highest when consecutive accesses were within 150 ft of one another and the frequency of crashes decreased substantively as spacing was increased to 300 ft and, particularly, 600 ft. With spacing beyond 600 ft, crash rates continued to decrease, although these improvements were less pronounced than at the lower range of values. These findings were generally consistent on multilane and two-lane highways.

scholarly journals Modeling Traffic Accident Occurrence at Hazardous Road Locations: A Case Study in Tunisia

2018 ◽  
Author(s):  
Fedy Ouni ◽  
Mounir Belloumi
Keyword(s):  
Goodness Of Fit ◽  
Negative Binomial ◽  
Prediction Models ◽  
Pearson Correlation ◽  
Surface Condition ◽  
Random Effect ◽  
Negative Binomial Model ◽  
Empirical Modeling ◽  
Binomial Model ◽  
Model Average

The purpose of the present study is to explore the linkage between Hazardous Road Locations-based crash counts and a variety of geometric characteristics, roadway characteristics, traffic flow characteristics and spatial features in the region of Sousse, Tunisia. For this purpose, collision data was collected from at 52 hazardous road sections including 1397 crash records for a 11-year monitoring period from January 1, 2004 to December 31, 2014 obtained from National Observatory for Information, Training, Documentation and Studies on Road Safety in Tunisia (NOITDRS). The matrix of Pearson correlation was used in order to avoid inclusion of both variables, which were highly correlated. Both the Random Effects Negative Binomial model and the Negative Binomial model were estimated. To evaluate the models, the Random Effect Negative Binomial model improves the goodness-of-fit compared to the Negative Binomial model. Average Daily Traffic volume, Curved alignment, Presence of public lighting, Visibility, Number of lane, Presence of vertical/horizontal sign, Presence of rural segment, Presence of drainage system, Roadway surface condition, Presence of paved shoulder and presence of major road were found as significant variables influencing accident occurrences. Overall, the current research contributes to the literature from empirical, modeling methodological standpoints since it was the first study conducted in Tunisia to use crash prediction models for hazardous road locations, and that portrays Tunisian reality. The research findings present advantageous insights on hazardous road locations in the region of Sousse, Tunisia and present useful planning tools for public authorities in Tunisia.

Identification of Accident Causal Factors and Prediction of Hazardousness of Intersection Approaches

2003 ◽  
Vol 1840 (1) ◽  
pp. 116-122 ◽  
Author(s):  
S. S. P. Kumara ◽  
H. C. Chin ◽  
W. M. S. B. Weerakoon
Keyword(s):  
Nonparametric Regression ◽  
Negative Binomial ◽  
Random Effect ◽  
Control Measures ◽  
Generalized Regression Neural Network ◽  
Subtractive Clustering ◽  
Total Production ◽  
Data Set ◽  
Causal Factors ◽  
Left Turn

Safety improvements were evaluated at signalized intersection approaches, where about 30% of road crashes occur in Singapore (in Singapore, vehicles are driven on the left side of the road). Identification of accident causal factors and prediction of hazardousness are essential tasks before safety treatments can be prescribed and prioritized. Statistical methods were used as a novel method for the identification of causal factors affecting accident frequencies, while nonparametric regression techniques were used for the prediction of intersection approach hazardousness. The statistical methodology used, the random-effect negative binomial model, indicates that uncontrolled left-turn slip roads, sight distances of less than 100 m, large numbers of signal phases, the use of permissive right-turn phases, the existence of horizontal curves, and total and left-turn volumes may increase the likelihood of accident occurrence. By nonparametric regression, the subtractive clustering methodology in fuzzy logic was used to derive an efficient and effective data set from the original data, which exhibited a high level of noise. This clustered data set was used to predict hazardousness. The prediction model, a generalized regression neural network, showed reasonable prediction accuracy. The model was capable of predicting hazardousness of about 65% for the total production data set, with a difference between the actual and the predicted values of less than 0.1. Moreover, the results suggest that the nonparametric regression network works well in multidimensional measurement spaces, in which hazardousness is assumed to be a function of several geometric, traffic, and traffic control measures.

scholarly journals Cardiovascular hospitalisation before and during the financial crisis among occupations in Taiwan

2019 ◽  
Vol 29 (Supplement_4) ◽  
Author(s):  
Y Chang
Keyword(s):  
Financial Crisis ◽  
Sex Education ◽  
Negative Binomial ◽  
Random Effect ◽  
Unskilled Worker ◽  
Research Database ◽  
Skilled Workers ◽  
Occupational Groups ◽  
2008 Financial Crisis ◽  
The 2008 Financial Crisis

Abstract Background Cardiovascular diseases (CVD) were related to financial stress. Little was known about the effects of financial crisis on cardiovascular health by occupations. This study examined CVD hospitalisations before and during the 2008 financial crisis among five occupational groups in Taiwan. Methods Data were collected from the Taiwan Survey on Hypertension, Hyperglycemia and Hyperlipidaemia 2007, including 4,673 participants aged 20 and above, categorized into five types of occupations, i.e., professional & manager (PM), office clerk & administrative staff (OA), skilled work (SW), unskilled worker (UW) and non-worker (NW). We abstracted their CVD hospitalisation records in the three years before (September 2005 to August 2008) and during the 2008 financial crisis (September 2008 to August 2011) from the National Health Insurance Research Database. Using incidence rate ratios (IRRs), we compared CVD hospitalisation of the first, second, third year from September 2008 to the three-year average before September 2008 for five occupational groups. Random effect negative binomial models were performed to estimate IRRs. Results After adjusting for covariates including age, sex, education, smoking, alcohol drinking, exercise and body mass index, there was an increase of CVD hospitalisation incidence for NW in the first year of the financial crisis (IRR=1.46, 95% Confidence Interval [95% CI]=1.19-1.77); in the second year, SW had a raised risk of CVD hospitalisation (IRR= 2.71, 95% CI = 1.59-4.60). For all occupational groups, the incidence rates of CVD hospitalisation reached the peak in the third year (PM: IRR=2.68, 95% CI = 1.05-6.83; OA: IRR=2.70, 95% CI = 1.18-6.19; SW: IRR=5.13, 95% CI = 2.89-9.09; UW: IRR=2.12, 95% CI = 1.02-4.41; NW: IRR=1.85, 95% CI = 1.18-2.67). Conclusions CVD hospitalisation of all occupations were affected by the financial crisis; when non-workers were the early victims, skilled workers may be the most vulnerable in the 2008 financial crisis. Key messages This study investigated the effects of the 2008 financial crisis on cardiovascular disease hospitalization by five occupational types in Taiwan. All occupations, particularly skilled workers, were affected by the financial crisis.

scholarly journals A comparison of zero-inflated and hurdle models for modeling zero-inflated count data

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Cindy Xin Feng
Keyword(s):  
Health Services ◽  
Count Data ◽  
Goodness Of Fit ◽  
Negative Binomial ◽  
Simulation Studies ◽  
Final Choice ◽  
Hurdle Models ◽  
Count Distribution ◽  
Careful Assessment

AbstractCounts data with excessive zeros are frequently encountered in practice. For example, the number of health services visits often includes many zeros representing the patients with no utilization during a follow-up time. A common feature of this type of data is that the count measure tends to have excessive zero beyond a common count distribution can accommodate, such as Poisson or negative binomial. Zero-inflated or hurdle models are often used to fit such data. Despite the increasing popularity of ZI and hurdle models, there is still a lack of investigation of the fundamental differences between these two types of models. In this article, we reviewed the zero-inflated and hurdle models and highlighted their differences in terms of their data generating processes. We also conducted simulation studies to evaluate the performances of both types of models. The final choice of regression model should be made after a careful assessment of goodness of fit and should be tailored to a particular data in question.

scholarly journals Identifying Temporal Aggregation Effect on Crash-Frequency Modeling

2021 ◽  
Vol 13 (11) ◽  
pp. 6214
Author(s):  
Bumjoon Bae ◽  
Changju Lee ◽  
Tae-Young Pak ◽  
Sunghoon Lee
Keyword(s):  
Traffic Safety ◽  
Negative Binomial ◽  
Random Effect ◽  
Temporal Correlation ◽  
Negative Binomial Regression ◽  
Spatiotemporal Analysis ◽  
Parameter Estimates ◽  
Crash Frequency ◽  
Crash Frequency Modeling ◽  
Using Data

Aggregation of spatiotemporal data can encounter potential information loss or distort attributes via individual observation, which would influence modeling results and lead to an erroneous inference, named the ecological fallacy. Therefore, deciding spatial and temporal resolution is a fundamental consideration in a spatiotemporal analysis. The modifiable temporal unit problem (MTUP) occurs when using data that is temporally aggregated. While consideration of the spatial dimension has been increasingly studied, the counterpart, a temporal unit, is rarely considered, particularly in the traffic safety modeling field. The purpose of this research is to identify the MTUP effect in crash-frequency modeling using data with various temporal scales. A sensitivity analysis framework is adopted with four negative binomial regression models and four random effect negative binomial models having yearly, quarterly, monthly, and weekly temporal units. As the different temporal unit was applied, the result of the model estimation also changed in terms of the mean and significance of the parameter estimates. Increasing temporal correlation due to using the small temporal unit can be handled with the random effect models.

610 Self-Reported Sleep and Circadian Characteristics Predict Future Substance Use: A Longitudinal Analysis from the NCANDA Study

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A240-A240
Author(s):  
Brant Hasler ◽  
Jessica Graves ◽  
Meredith Wallace ◽  
Stephanie Claudatos ◽  
Fiona Baker ◽  
...  
Keyword(s):  
Risk Factors ◽  
Substance Use ◽  
Sleep Duration ◽  
Daytime Sleepiness ◽  
Parental Education ◽  
Negative Binomial ◽  
Longitudinal Design ◽  
Random Effect ◽  
Cannabis Use ◽  
Increased Risk

Abstract Introduction Growing evidence indicates that sleep characteristics predict later substance use and related problems during adolescence and young adulthood. However, most prior studies have assessed a limited range of sleep characteristics, studied only a narrow age span, and included relatively few follow-up assessments. Here, we used multiple years of data from the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA) study, which spans the adolescent period with an accelerated longitudinal design, to examine whether multiple sleep characteristics in any year predict substance use the following year. Methods The sample included 831 participants (423 females; age 12–21 years at baseline) from NCANDA. Sleep variables included the previous year’s circadian preference, sleep quality, daytime sleepiness, timing of midsleep (weekday and weekend), and sleep duration (weekday and weekend). Each sleep variable’s association with the subsequent year’s substance use (cannabis use or alcohol binge severity) across years 1–5 was tested separately using generalized linear mixed models (zero-inflated Negative Binomial for cannabis; ordinal for binge severity) with age, sex, race, visit, parental education, previous year’s substance use (yes/no) as covariates and subject as a random effect. Results With regard to cannabis use, greater eveningness and shorter weekday sleep duration predicted an increased risk for additional days of cannabis use the following year, while greater eveningness and later weekend midsleep predicted a greater likelihood of any cannabis use the following year. With regard to alcohol binge severity, greater eveningness, greater daytime sleepiness, and shorter sleep duration (weekday and weekend) all predicted an increased risk for more severe alcohol bingeing the following year. Post-hoc stratified analyses indicated that some of these associations may differ between high school-age and college-age participants. Conclusion Our findings extend prior work, indicating that eveningness and later sleep timing, as well as shorter sleep duration, especially on weekdays, are risk factors for future cannabis use and alcohol misuse. These results underscore a need for greater attention to sleep characteristics as potential risk factors for substance use in adolescents and young adults and may inform future areas of intervention. Support (if any) Grants from NIH: R01AA025626 (Hasler) and U01AA021690 (Clark) and UO1 AA021696 (Baker & Colrain)

scholarly journals GLM-Based Flexible Monitoring Methods: An Application to Real-Time Highway Safety Surveillance

Symmetry ◽  
2021 ◽  
Vol 13 (2) ◽  
pp. 362
Author(s):  
Arshad Jamal ◽  
Tahir Mahmood ◽  
Muhamad Riaz ◽  
Hassan M. Al-Ahmadi
Keyword(s):  
Real Time ◽  
Control Charts ◽  
Negative Binomial ◽  
Highway Safety ◽  
Monitoring Methods ◽  
Count Data Models ◽  
Crash Data ◽  
Safety Surveillance ◽  
Study Results ◽  
Best Fit

Statistical modeling of historical crash data can provide essential insights to safety managers for proactive highway safety management. While numerous studies have contributed to the advancement from the statistical methodological front, minimal research efforts have been dedicated to real-time monitoring of highway safety situations. This study advocates the use of statistical monitoring methods for real-time highway safety surveillance using three years of crash data for rural highways in Saudi Arabia. First, three well-known count data models (Poisson, negative binomial, and Conway–Maxwell–Poisson) are applied to identify the best fit model for the number of crashes. Conway–Maxwell–Poisson was identified as the best fit model, which was used to find the significant explanatory variables for the number of crashes. The results revealed that the road type and road surface conditions significantly contribute to the number of crashes. From the perspective of real-time highway safety monitoring, generalized linear model (GLM)-based exponentially weighted moving average (EWMA) and cumulative sum (CUSUM) control charts are proposed using the randomized quantile residuals and deviance residuals of Conway–Maxwell (COM)–Poisson regression. A detailed simulation-based study is designed for predictive performance evaluation of the proposed control charts with existing counterparts (i.e., Shewhart charts) in terms of the run-length properties. The study results showed that the EWMA type control charts have better detection ability compared with the CUSUM type and Shewhart control charts under small and/or moderate shift sizes. Finally, the proposed monitoring methods are successfully implemented on actual traffic crash data to highlight the efficacy of the proposed methods. The outcome of this study could provide the analysts with insights to plan sound policy recommendations for achieving desired safety goals.

Does Displaying Safety Messages on Dynamic Message Signs have Measurable Impacts on Crash Risk?

2021 ◽  
pp. 036119812110444
Author(s):  
Megat-Usamah Megat-Johari ◽  
Nusayba Megat-Johari ◽  
Peter T. Savolainen ◽  
Timothy J. Gates ◽  
Eva Kassens-Noor
Keyword(s):  
Negative Binomial ◽  
Driver Behavior ◽  
Field Research ◽  
Crash Risk ◽  
Traffic Crashes ◽  
Crash Data ◽  
Safety Issues ◽  
Dynamic Message Signs ◽  
Safety Message ◽  
Message Signs

Transportation agencies have increasingly been using dynamic message signs (DMS) to communicate safety messages in an effort to both increase awareness of important safety issues and to influence driver behavior. Despite their widespread use, evaluations as to potential impacts on driver behavior, and the resultant impacts on traffic crashes, have been very limited. This study addresses this gap in the extant literature and assesses the relationship between traffic crashes and the frequency with which various types of safety messages are displayed. Safety message data were collected from a total of 202 DMS on freeways across the state of Michigan between 2014 and 2018. These data were integrated with traffic volume, roadway geometry, and crash data for segments that were located downstream of each DMS. A series of random parameters negative binomial models were estimated to examine total, speeding-related, and nighttime crashes based on historical messaging data while controlling for other site-specific factors. The results did not show any significant differences with respect to total crashes. Marginal declines in nighttime crashes were observed at locations with more frequent messages related to impaired driving, though these differences were also not statistically significant. Finally, speeding-related crashes were significantly less frequent near DMS that showed higher numbers of messages related to speeding or tailgating. Important issues are highlighted with respect to methodological concerns that arise in the analysis of such data. Field research is warranted to investigate potential impacts on driving behavior at the level of individual drivers.

Sign in / Sign up

Export Citation Format

Share Document