Spatial clustering of events on a network

In this paper a methodology is proposed to compute spatial concentrations of point-based events on a network. The distance along the network is used as a measure of the spatial closeness of events. The network is divided into statistical units, based on a random distribution of points of measurement and corresponding network segments, which are the statistical units of reference. For each segment a dangerousness index is computed which indicates the distance-weighted number of traffic accidents in the neighbourhood. The statistical significance of clusters of accidents is tested using a Monte Carlo simulation. The methodology is applied to traffic accidents to detect dangerous locations on the road network of the city of Brussels in Belgium.