This paper develops an empirical model of the relationship between road tra
ffic accidents and traffic flows. The analysis focuses on the accident exte
rnality, which is determined mainly by the difference between the marginal
and average risks. The model is estimated using a new data-set which combin
es hourly London traffic count data from automated vehicle recorders togeth
er with police records of road accidents. The accident-flow relationship is
seen to vary considerably between different road classes and geographical
areas. More importantly, even having controlled for these and other differe
nces, the accident externality is shown to vary significantly with traffic
flows. In particular, while the accident externality is typically close to
zero for low to moderate traffic flows, it increases substantially at high
traffic flows.