Speeding triples the odds of crashing, AAA finds.

Drivers who speed faster than surrounding traffic are nearly three times as likely to be involved in accidents as those who do not, a new study by the AAA Foundation for Traffic Safety finds.

Using data collected during the National Highway Traffic Safety Administration's 100-car, naturalistic driving study, the foundation identified four specific driving behaviors that it concludes can be conclusively linked with an increased risk of being involved in a crash or near-crash. The study, which was conducted by the Virginia Tech Transportation Institute, monitored the driving behaviors of 109 primary drivers and 132 secondary drivers in the Washington D.C., area.

As part of the study, vehicle and electronic sensors were placed in the drivers' vehicles. The drivers then were studied over the course of the year, as researchers analyzed data on a number of driving behaviors to determine the relative risks posed by each.

In addition to the increased risks posed by speeding, the study concludes that driving while drowsy also triples the odds of being involved in an accident. Accident risks doubled for drivers who took their eyes off the road for more than two seconds, as well as for those who exhibited "aggressive" driving behaviors, AAA concluded.

The highest-risk drivers in the study, which it defined as the 12.5% of the sample with the highest rates of crashes, near-crashes and incidents per miles driven, were shown to be less likely to wear a safety belt and more likely to drive while drowsy than the lowest-risk drivers, defined as the 12.5% with the lowest rates of crashes, near-crashes and incidents per miles driver. At 219.5 adverse incidents for every 10,000 miles driven, the high-risk drivers were nearly 100 times riskier than the lowest-risk drivers, who had only 2.1 incidents per 10,000 miles driven.

"The primary difference between a crash and a near-crash is a successful evasive maneuver," the researchers wrote. "Thus, crashes lead to property damage, injury and possibly death, but near-crashes do not, even though they have similar properties. Including both near-crash and crash events in the calculation of odds ratios greatly improves statistical precision of the estimates, and appears to be a promising technique for use in future research."

Motor vehicle crashes accounted for a total of 42,643 deaths in 2003, killing 14.66 out of every 100,000 Americans, according to the National Highway Traffic Safety Administration. In 2000, the total economic cost of traffic fatalities was approximately $230.6 billion, including $61 billion in lost productivity, $59 billion in property damage, and $32.6 billion in travel delays.