The Diffusion of Crime in the Metropolis: A Step-By-Step Analysis

Meir Gross
Simon Hakim


DOI: 10.2190/Q92G-RKCB-AJN9-5CWA

Abstract

This paper presents a practical statistical approach to analyzing the causes of property crimes committed in suburban communities which differs from the common hypothesis-testing methodology of social scientists by integrating theoretical models with extensive data analysis. The method examines the first few samples establishing a qualitative assessment of the data, then it plots relationships between variables to arrive at various functional forms to be used in later modelling. Before constructing a regression model, simple bivariate correlations are checked to identify highly collinear variables and to exclude variables not deserving further investigation. Thus, the output of each stage in the analysis is the input to the next stage. The method attempts to understand "what the data are trying to tell us" before proceeding to multiple regression analyses.

The article concludes with a theoretically sound crime attraction model which explains the attraction of property crimes to suburban localities. The data base for the study was drawn from the New Jersey suburbs of Philadelphia.


Creative Commons License This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License.