A Hierarchical Mixed Logit Model of Hybrid Involved Crash Severities
In this paper, the authors present a mixed logit model of the severity of a crash involving hybrid vehicles. The most severe outcome of the crash is modeled. Crash data from the Washington State Department of Transportation was obtained for the period 2006-2010 and hybrid vehicle identification data was added to the database. Data such as vehicle width, weight, horsepower, turning radius, drivetrain and ground clearance was added. It was found that the factors associated with the most severe outcome of the crash included crash specific variables relating to occupant count, vehicle involvement, collision type, crash site roadway alignment, functional class of roadway, pavement surface condition at the time of the crash, and the maximum occupant age (in multi-occupant crashes). The most severe outcome was based on three injury categories, namely, property damage only, possible injury and injury (inclusive of evident, disabling and fatal.) It was also determined that random effects are plausible in the possible injury severity function. Heterogeneity in means due to vehicle age appeared significant; yet, the standard deviation of the vehicle involvement coefficient in the property damage severity function was not statistically significant. Heteroskedasticity in the random parameter variances was also tested as a function of hybrid vehicle weight and width; the random effect is weakly heteroskedastic. The results are from an analysis of 1,665 crashes; while the heteroskedastic effects and heterogeneity in means appear inconclusive, they suggest that random effects with parameter heteroskedasticity and heterogeneous means cannot be ignored in hybrid crash severity analyses.
-
Supplemental Notes:
- This paper was sponsored by TRB committee ABJ80 Standing Committee on Statistical Methods. Alternate Title: Heterogeneity in Hybrid-Involved Crash Severities: Exploratory Analysis Using Hierarchical Mixed Logit Model with Hierarchical Hybrid Vehicle Attributes
-
Corporate Authors:
500 Fifth Street, NW
Washington, DC United States 20001 -
Authors:
- Huang, Shuaiqi
- Seraneeprakarn, Puttipan
- Shankar, Venkataraman
-
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: References; Tables;
- Pagination: 18p
- Monograph Title: TRB 95th Annual Meeting Compendium of Papers
Subject/Index Terms
- TRT Terms: Crash characteristics; Crash injuries; Crash severity; Data analysis; Hybrid vehicles; Injury severity
- Geographic Terms: Washington (State)
- Subject Areas: Highways; Safety and Human Factors; Vehicles and Equipment;
Filing Info
- Accession Number: 01592846
- Record Type: Publication
- Report/Paper Numbers: 16-5162
- Files: TRIS, TRB, ATRI
- Created Date: Mar 7 2016 10:19AM