Although the Federal Motor Carrier Safety Administration’s data-driven analysis model — called SafeStat — is much better than random selection at identifying high-risk carriers for additional oversight, a statistical approach would be even better, the General Accounting Office said.
In a new report, GAO noted that SafeStat is built on a number of expert judgments rather than using statistical approaches, such as a regression model. For example, SafeStat designers weighted more recent motor carrier crashes twice as much as less recent ones — concluding that more recent crashes were stronger indicators of future crashes. GAO estimates that if FMCSA used a negative binomial regression model, it could increase its ability to identify high-risk carriers by about 9 percent over SafeStat.
According to GAO, Department of Transportation officials agree in principle that a statistical approach is preferred, but they are concerned about the greater sensitivity of this approach to problems with reported crash data. But GAO found that late-reported crash data had a small effect on SafeStat’s ability to identify carriers that posed high crash risks in 2004.
For a copy of the GAO report, click here. For a copy of the report’s highlights, click here.