INJURY ACCIDENT PREDICTION MODELS FOR SIGNALIZED INTERSECTIONS

An intuitive methodology for developing accident prediction models for signalized intersections based on the Traffic Accident Surveillance and Analysis System (TASAS) in California is illustrated. A fairly new grouping and classifying technique called Classification and Regression Trees (CART) was used as a building block for developing injury accident models. The proposed methodology is a three-level procedure with a "tree" structure for easy interpretation and application. Macroscopic-type models for injury accidents per year are derived, and the following factors have been found to be significant: traffic intensity, proportion of cross street traffic, intersection type, signal type, number of lanes on cross streets and main streets, and left turn arrangements. On the basis of the results, it is also apparent that the models derived from the proposed methodology and TASAS provide more intuition and flexibility than the existing models used in California and other models derived from both site observations and accident record systems.

• Record URL:
  • http://onlinepubs.trb.org/Onlinepubs/trr/1988/1172/1172-007.pdf
• Record URL:
  • https://scholar.google.com/scholar_lookup?title=INJURY+ACCIDENT+PREDICTION+MODELS+FOR+SIGNALIZED+INTERSECTIONS&author=M.+Lau&author=A.+May&publication_year=1988
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/0309047099
• Supplemental Notes:
  • This paper appears in Transportation Research Record No. 1172, Traffic Accident Analysis and Roadway Visibility. Distribution, posting, or copying of this PDF is strictly prohibited without written permission of the Transportation Research Board of the National Academy of Sciences. Unless otherwise indicated, all materials in this PDF are copyrighted by the National Academy of Sciences. Copyright © National Academy of Sciences. All rights reserved
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Lau, Michael Yiu-Kim
  • May Jr, Adolf D
• Publication Date: 1988

Media Info

• Features: Figures; References; Tables;
• Pagination: p. 58-67
• Monograph Title: TRAFFIC ACCIDENT ANALYSIS AND ROADWAY VISIBILITY
• Serial:
  • Transportation Research Record
  • Issue Number: 1172
  • Publisher: Transportation Research Board
  • ISSN: 0361-1981

Subject/Index Terms

• TRT Terms: Crashes; Databases; Forecasting; Injuries; Mathematical models; Signalized intersections
• Subject Areas: Highways; Safety and Human Factors; I81: Accident Statistics;

Filing Info

• Accession Number: 00481004
• Record Type: Publication
• ISBN: 0-309-04709-9
• Files: TRIS, TRB, ATRI
• Created Date: Mar 31 1989 12:00AM