Sina Tehranchi

This research presents a Geographic Information Systems (GIS) and spatial analysis approach based on the global spatial autocorrelation of road traffic injuries for identifying spatial patterns. A locational spatial autocorrelation was also used for identifying traffic injury at spatial level. Data for this research study were acquired from Canadian Institute for Health Information (CIHI) based on 2004 and 2011. Moran’s I statistics were used to examine spatial patterns of road traffic injuries in the Greater Toronto Area (GTA). An assessment of Getis-Ord Gi* statistic was followed as to identify hot spots within the study area. The results revealed that Peel and Durham regions have the highest collision rate for other motor vehicle with motor vehicle. Geographic weighted regression (GWR) technique was conducted to test the relationships between the dependent variable, number of road traffic injury incidents and independent variables such as number of seniors, low education, unemployed, vulnerable groups, people smoking and drinking, urban density and average median income. The result of this model suggested that number of seniors and low education have a very strong correlation with the number of road traffic injury incidents.