The Spatial Patterning of County Homicide Rates: An Application of Exploratory Spatial Data Analysis

The possibility that homicides can spread from one geographic area toanother has been entertained for some time by social scientists, yetsystematic efforts to demonstrate the existence, or estimate the strength,of such a diffusion process are just beginning. This paper uses exploratoryspatial data analysis (ESDA) to examine the distribution of homicides in 78counties in, or around, the St. Louis metropolitan area for two timeperiods: a period of relatively stable homicide (1984–1988) and aperiod of generally increasing homicide (1988–1993). The findingsreveal that homicides are distributed nonrandomly, suggestive of positivespatial autocorrelation. Moreover, changes over time in the distribution ofhomicides suggest the possible diffusion of lethal violence out of onecounty containing a medium-sized city (Macon County) into two nearbycounties (Morgan and Sangamon Counties) located to the west. Althoughtraditional correlates of homicide do not account for its nonrandom spatialdistribution across counties, we find some evidence that more affluentareas, or those more rural or agricultural areas, serve as barriers againstthe diffusion of homicides. The patterns of spatial distribution revealedthrough ESDA provide an empirical foundation for the specification ofmultivariate models which can provide formal tests for diffusion processes.