|
|
|
Title: Exploration of Macro-level Effects for Segment and Intersection Crash Modeling
Accession Number: 01657955
Record Type: Component
Abstract: It is acknowledged that crash occurrence at segments and intersections could be affected by multilevel factors. Omission of important explanatory variables could result in biased and inconsistent parameter estimates. This paper contributes to the literature on traffic safety research for segments and intersections by examining the macro-level effects which are always excluded or ignored. A Bayesian hierarchical model is proposed to incorporate the macro-level factors including not only macro-level explanatory variables but also total segment- and intersection-crash counts aggregated based on zones. In addition, a joint modeling structure is adopted to investigate the spatial autocorrelation between intersection and their connecting segments. The proposed model is evaluated by comparing it with its three counterparts: a model considering micro-level factors only, one hierarchical model considering macro-level effects with random effect terms only, and one hierarchical model considering macro-level effects with explanatory variables based on zones. The results indicate that the models considering macro-level effects outperform the road entity crash models. In addition, the proposed model has improved performance, which validates the concept of considering macro-level effects through both explanatory variables and total crashes based on zones. In addition, significant spatial autocorrelation could be found between intersections and their connecting segments, supporting the modeling structure to analyze crashes at various types of road entities. Finally, the proposed model provides more valuable insights about the crash occurrence at segments and intersections by revealing both micro- and macro-level factors.
Supplemental Notes: This paper was sponsored by TRB committee ANB25 Standing Committee on Highway Safety Performance. Exploration of Macrolevel Effects for Segment and Intersection Crash Modeling: This is an alternate title.
Report/Paper Numbers: 18-00618
Language: English
Authors: Pagination: 7p
Publication Date: 2018
Conference:
Transportation Research Board 97th Annual Meeting
Location:
Washington DC, United States Media Type: Digital/other
Features: References; Tables
TRT Terms: Uncontrolled Terms: Subject Areas: Highways; Planning and Forecasting; Safety and Human Factors
Source Data: Transportation Research Board Annual Meeting 2018 Paper #18-00618
Files: TRIS, TRB, ATRI
Created Date: Jan 8 2018 10:10AM
|
0000-0001-7901-3995