United States Department of Transportation
i
Identifying Highly Correlated Variables Relating to the Potential Causes of Reportable Wisconsin Traffic Crashes
-
2019-07-01
-
[PDF-4.89 MB]
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:September 2016 - August 2019
-
Corporate Publisher:
-
Abstract:The goal of this research project is to provide the Wisconsin Department of Transportation (WisDOT) with the state of art methodologies for identifying the most pertinent behavioral and engineering variables relating to reportable crashes. In this regard, an extensive literature review has been performed to summarize the latest progress in crash modeling from a broad range of crash factors and analytical methodologies. A three-pronged approach has been taken to study the complexity of crash occurrence in diverse and varying contexts, including area-level modeling (census tract), site-specific modeling (roadway segment), and event-oriented modeling (crash events). More than 100 variables have been evaluated in over a dozen statistical models. New methodologies have been developed to effectively quantify the impact of behavioral variables on crash counts, or account for their absence when they are not available. Moreover, the effect of risky driving behaviors on traffic safety has been measured using Wisconsin traffic citation data. In addition, street corridor-based pedestrian and bike crash prediction models have been calibrated by data collected from various new sources throughout the state. The findings in the study will serve as an important and comprehensive reference for traffic safety professionals and researchers.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
