Determining Contributory Factors Affecting Rear-end Crashes Using Hurdle Count Models
The main objective of this study is to identify which set of explanatory variables related to roadway physical and operational characteristics are associated with rear-end crashes. The second objective is to check the applicability of hurdle count models, which have rarely been applied in the safety literature. To do this, four count models including standard Poisson (PO), negative binomial (NB), hurdle Poisson (HP), and hurdle negative binomial (HNB) models were developed and compared using crash data collected on 313 segments of Malaysian federal roads. The data used in this study includes a total of 665 records of rear-end (RE) crashes occurred over a 3-year period from 2007 through 2009. The results showed that the HNB model outperforms other count models. In addition, there was an evidence of overdispersion in the crash data where both excess zero counts and unobserved heterogeneity together contributed to the overdispersion parameter. The HNB modelling results showed that average daily traffic, heavy vehicle percentage, access point, and land use were associated with higher RE crash frequency. Regarding the dichotomous process, average daily traffic, speed limit, horizontal curvature, shoulder width, number of lanes, and side friction were found to be associated with the probability of non-zero RE crashes.
-
Supplemental Notes:
- This paper was sponsored by TRB committee ABJ80 Standing Committee on Statistical Methods.
-
Corporate Authors:
500 Fifth Street, NW
Washington, DC United States 20001 -
Authors:
- Hosseinpour, Mehdi
- Yahaya, Ahmad Shukri
- Ahadi, Mohammad Reza
- Asoode, Razie
- Momeni, Hojr
-
Conference:
- Transportation Research Board 95th Annual Meeting
- Location: Washington DC, United States
- Date: 2016-1-10 to 2016-1-14
- Date: 2016
Language
- English
Media Info
- Media Type: Web
- Features: Figures; References; Tables;
- Pagination: 16p
- Monograph Title: TRB 95th Annual Meeting Compendium of Papers
Subject/Index Terms
- TRT Terms: Average daily traffic; Crash causes; Crash characteristics; Heavy vehicles; Highway safety; Land use; Rear end crashes; Vehicle mix
- Geographic Terms: Malaysia
- Subject Areas: Highways; Safety and Human Factors; I81: Accident Statistics; I82: Accidents and Transport Infrastructure;
Filing Info
- Accession Number: 01588773
- Record Type: Publication
- Report/Paper Numbers: 16-1629
- Files: TRIS, TRB, ATRI
- Created Date: Jan 29 2016 9:32AM