Abstract

Road fatalities in the USA have recently decreased, and these reductions are greater than the corresponding reductions in the amount of driving. A multiple regression analysis was performed on monthly data from January 2007 through December 2008. The dependent variable was the number of road fatalities. The independent variables were distance driven, proportion of driving on rural roads, and the average price of unleaded gasoline as a proxy for the proportion of leisure driving. The results suggest that the larger-than-expected fall in road fatalities is partly a consequence of the disproportional decreases in rural driving (which is more risky than urban driving) and leisure driving (which is more risky than commuter driving).