U.S. Department of Transportation
Federal Highway Administration
1200 New Jersey Avenue, SE
Washington, DC 20590
202-366-4000
Federal Highway Administration Research and Technology
Coordinating, Developing, and Delivering Highway Transportation Innovations
 |
| This report is an archived publication and may contain dated technical, contact, and link information |
|
Publication Number: FHWA-RD-98-133
Date: October 1998 |
||
Accident Models for Two-Lane Rural Roads: Segment and IntersectionsTABLE OF CONTENTS
Average Daily Traffic (ADT) Lane Width, Shoulder Width, and Shoulder Type Horizontal and Vertical Alignment Roadside and Terrain Condition Speed Driveways Traffic Flow Control Type Sight Distance and Alignment
THE POPULATIONS AND SAMPLE SELECTION Minnesota Segments Minnesota Intersections Washington Segments Washington Intersections HSIS Data Minnesota Photologs Minnesota Construction Plans Washington Videotapes Weather Data Miscellaneous Investigations Accident Data Traffic Data Alignment Data Location Uncertainties Time Uncertainties Miscellaneous Limitations
Accident Variables Traffic Variables Horizontal Alignment Variables Vertical Alignment Variables Angle Variables Miscellaneous Variables Minnesota versus Washington Segments versus Intersections Minnesota Sample versus Population Segment Accidents Three-legged Intersection Accidents Four-legged Intersection Accidents Other Bivariate Relationships
POISSON AND NEGATIVE BINOMIAL MODELING TECHNIQUES The Poisson and Negative Binomial Models Model Evaluation - Overdispersion Model Evaluation - Goodness of Fit The State Variable The Exposure Variable Lane Width and Shoulder Width Horizontal and Vertical Curve Variables Grade, Roadside Hazard Rating, Driveway Density, and Other Variables Poisson versus Negative Binomial The Extended Negative Binomial Traffic Alignment, Channelization, and Speed Roadside Variables - Number of Driveways and Hazard Rating The Angle Variable Negative Binomial Models - Minnesota versus Washington Additional Negative Binomial Runs Negative Binomial Models for Injury Accidents Final Intersection Models Theory Results
6. VALIDATION AND FURTHER ANALYSIS Validation Techniques Minnesota Models versus Later Minnesota Data Minnesota Models versus Washington Data Washington and Combined Segment Models versus Minnesota Data EXPLANATORY VALUE OF FINAL MODELS
APPENDIX 1 - STATISTICS ON THE MINNESOTA POPULATIONS APPENDIX 2 - FINAL MODELS IN METRIC UNITS
|
