A temporal, spatial, and spatial-temporal autocorrelation analysis of highway accidents on the indiana toll road from 1983 to 1987 is presented. Applications of von Neumann's ratio, Moran's I, nearest-neighbour analysis, and a spatial-temporal autocorrelation coefficient to a transportation network situation are illustrated. Applications of these methods to transport network attributes, such as accidents, have not appeared previously. The main objectives are to determine whether these techniques are sensitive enough to distinguish different patterns in the accident distributions and whether these patterns are explainable. The analysis involved 10 sets of accident data, categorised by date of occurrence and location on an east-west roadway. Only 2 of the 10 revealed positive temporal autocorrelation (clustering in time), 5 revealed positive spatial autocorrelation (clustering in space), and between 6 and 9, depending on the method used, revealed positive spatial-temporal autocorrelation (clustering in time and space). These results suggest that observed autocorrelation sin accidents are a function of weather conditions or traffic volumes, or a combination of the two.
Abstract