• Federal Highway Administration >
• Publications >
• Research Publications >
• 10024 >
• Ch03.Cfm >
• Development of a Speeding-Related Crash Typology

Development of a Speeding-Related Crash Typology

PDF files can be viewed with the Acrobat® Reader®

DATA USED

Since a goal of the study was to explore questions as they relate to SR crashes in the United States, data were used from two major national crash databases–the National Automotive Sampling System's General Estimates System (NASS GES, referred to as GES) and FARS.^(9,1) While NASS CDS contains more detailed crash investigation data, its sample size of approximately 5,000 cases per year, which is only partially comprised of SR crashes,  was considered too small for this analysis.⁽⁸⁾ GES data are derived from a nationally representative sample of police–reported motor vehicle crashes of all types from minor to fatal.⁽⁹⁾ Approximately 60,000 police accident reports are included each year. Sample weights are assigned to each crash based on a sampling protocol. Using the weight, the sample can be extrapolated to represent the approximately six million U.S. crashes occurring each year. FARS is a census of all fatal crashes in the United States, showing approximately 40,000 fatal crashes in 2005.⁽¹⁾ To ensure that findings were as current as possible, data from 2005, which is the latest year available in each file, were used in these analyses.

The FHWA was interested in examining speeding using a disaggregated definition where "too fast for conditions" and "exceeding posted speed" would be analyzed separately since the appropriate countermeasures could differ for these two types of SR crashes. However, data available in GES and FARS only make it possible to define SR crashes with a broader definition, which consists of drivers either exceeding the posted speed limit or driving too fast for conditions. To better examine the possible effects of using only this combined definition, researchers used data from two States in FHWA's Highway Safety Information System (HSIS) that allowed the use of the more restrictive definition for the second part of the study. HSIS is the only multistate database containing annual files of not only crash data but also linkable roadway inventory and traffic volume data. While HSIS is usually used to conduct studies of changes in safety risk due to changes in roadway features (e.g., the effects of an intersection design change on safety), the linkability of the files allows one to enhance the crash variables with additional roadway variables, which was used in this study. Enhanced crash data from North Carolina from 2002–2004 and Ohio from 2003–2005 were used to ensure adequate sample sizes.

FHWA-HRT-10-024