Analyzing the dynamics of homicide patterns in Chicago: ESDA and spatial panel approaches

This paper studies the relationship between homicide rate and socioeconomic factors at community area level in Chicago from 1960 to 1995. Most of prior studies of social disorganization theory are based on cross-sectional spatial regression or longitudinal studies. This research integrates space and time in testing social disorganization theory. First, exploratory spatial data analysis (ESDA) is used to examine dynamic spatial patterns of these indicators. This investigation justifies the estimation of homicide rates across community areas through panel-data models that extend to include spatial lag and spatial error autocorrelation.

Research highlights
► This research conducts an empirical study of both the spatial and temporal aspects of homicide patterns at the community area level.
► Spatial panel regression is considered a solution to examine the space–time relationship between crime and neighborhood characteristics.
► Historically formed neighborhoods are desirable units of analysis in social disorganization research.