This paper presents a GIS approach based on spatial autocorrelation analysis of pedestrian-vehicle crash data for identification and ranking of unsafe bus stops. Instead of crash counts, severity indices are used for analysis and ranking. Moran's I statistic is employed to examine spatial patterns of pedestrian-vehicle crash data. Getis-Ord Gi* statistic is used to identify the clustering of low and high index values and to generate a pedestrian-vehicle crash hot spots map. As recent studies have shown strong correlations between pedestrian-vehicle crashes and transit access, especially bus stops, bus stops in pedestrian-vehicle crash hot spots are then selected and ranked based on the severity of pedestrian-vehicle crashes in their vicinities. The proposed approach is evaluated using 13 years (1996–2008) of pedestrian-vehicle crash data for the Adelaide metropolitan area. Results show that the approach is efficient and reliable in identifying pedestrian-vehicle crash hot spots and ranking unsafe bus stops.
Truong, Long T & Somenahalli, Sekhar V.
Using GIS to Identify Pedestrian-Vehicle Crash Hot Spots and Unsafe Bus Stops.
Journal of Public Transportation, 14 (1): 99-114.
Available at: https://scholarcommons.usf.edu/jpt/vol14/iss1/6