Modeling Local-Scale Violent Crime Rate: A Comparison of Eigenvector Spatial Filtering Models and Conventional Spatial Regression Models

Environmental factors have both direct and indirect impacts on crime behavior decision making. This study aimed to examine what degree the occurrences of violent crimes can be affected by social built environment over space. Although a few studies attempted model rate using spatial regression models, there is lack comparison models. Particularly, eigenvector filtering type models has reportedly been effective in urban regional studies, but it not widely applied data. In this study, we whether outperforms conventional types modeling rates Moreover, investigate land use mix street connectivity as routine activity theory explained. empirical two (i.e., error model) were selected estimated successfully local-scale across New York City. The outperform well nonspatial Model estimation results show that assaults robberies) determined socioeconomic thereby environmental affect crimes. contributions offer insights planning policymaking toward prevention. offers new evidence increasing enhance activity, reducing Policymakers planners should continue through connectivity. addition, are advocated for or other applications studies.