Comparative modeling approaches for understanding urban violence

Tony H Grubesic; Elizabeth A Mack; Maria T Kaylen

doi:10.1016/j.ssresearch.2011.07.004

Comparative modeling approaches for understanding urban violence

Soc Sci Res. 2012 Jan;41(1):92-109. doi: 10.1016/j.ssresearch.2011.07.004. Epub 2011 Jul 28.

Authors

Tony H Grubesic¹, Elizabeth A Mack, Maria T Kaylen

Affiliation

¹ Geographic Information Systems and Spatial Analysis Laboratory, College of Information Science and Technology, Drexel University, Philadelphia, PA 19104, United States.

PMID: 23017699
DOI: 10.1016/j.ssresearch.2011.07.004

Abstract

The purpose of this paper is to provide a comparative analysis of three different modeling approaches for exploring structural theories of violence. Specifically, ordinary least squares regression, geographically weighted regression and data envelopment analysis will be utilized to evaluate violent crime. This type of analysis expands upon traditional theory testing by deepening our understanding of differences in crime generation and its underlying demographic and socio-economic stimuli via different methodological lenses. A case study for the city of Cincinnati, Ohio is presented and the results suggest that a combination of approaches is likely the best strategy for evaluating violence in urban areas.