Mapping crime – Hate crimes and hate groups in the USA: A spatial analysis with gridded data

By Michael Jendrykea, , Stephen C. McClure

From time to time the popular media draws attention to hate crimes and hate groups, evoking images of NaziGermany and the rise of fascism. The geographic association between hate groups and hate crimes is uncertain. In this research we ask whether hate crimes are co-located and correlated to the presence of hate groups to explore a potential association between these two phenomena. Publicly available point level data on hate crimes and hate groups collected by the Southern Poverty Law Center (SPLC) were aggregated to unitary framework of hexagonal grid cells of a Discrete Global Grid System (DGGS) at multiple scales for consistent analysis. We explore the effects of proximity by interpreting a co-location map, deploying a Geographically Weighted Regression (GWR) for count data, and apply a Spatial Lag Model (SLM) at multiple scales, to ascertain the effects of the size of the aggregation units on the relationship between hate groups and hate crimes. Controlled or uncontrolled for spatial dependence, at all scales, the Spatial Lag Model (SLM) shows that an average of 39.5% of the hate crimes was correlated with hate groups. These results are consistent with the existing research but show that in most instances spatial dependence was present, regardless of the size of the aggregation unit or the distance to neighboring cells. Our future research will consider additional racial, economic and social variables using a DGGS.

Applied Geography. Volume 111, October 2019, 102072