Assessment of spatial clustering of accidents and hotspots spatial densities was
carried out following Moran’s I method of spatial autocorrelation, Getis-Ord Gi* statistics and point Kernel density
functions. The accidents as a whole show a clustered nature while the comparison of spatio-temporal break ups
indicates random distribution in certain classes. The Kernel density surface, estimated from the results of hotspot
analysis delineates the road stretches as well as isolated zones where the hotspots are concentrated. The results can be
effectively used by various agencies for adopting better planning and management strategies for improved traffic
conditions as well as accident reduction.