Pondering Products of Place-Level Distances: A Reply to Reinhart
- 213 Downloads
In “Crime Places in Context: An Illustration of the Multilevel Nature of Hotspot Development,” we built upon work in environmental criminology to provide a “simple” statistical test of the theoretical idea that crime hotspots form at the nexus of overlapping “layers” of crime potential—including activity nodes, movement paths, and environmental backcloth. By “simple,” we mean that our statistical analysis consisted of estimating the number of repeat crime incidents at crime places in Cincinnati using just four key variables: place-level distance to nearest carry-out liquor store, place-level distance to nearest on-premises drinking establishment, place-level distance to nearest bus route, and block-group-level density of commercial establishments. The conceptual and statistical issues raised by the hypothesized interplay among these four key variables, however, was far from simple, which is precisely why we chose to “start small,” variable-wise, in illustrating a statistical test of...
KeywordsCrime and place Environmental criminology Discordance 3-way product term 3-way interaction Deviance statistics
- Fox J (2016) Applied regression analysis and generalized linear models. Sage, New YorkGoogle Scholar
- Hanushek E, Jackson J (1977) Statistical methods for social scientists. Elsevier, New YorkGoogle Scholar
- Reinhart A (2016) Response to “crime places in context.” J Quant Criminol. doi: 10.1007/s10940-016-9299-4