418
Views
1
CrossRef citations to date
0
Altmetric
Articles

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

, , &
Pages 312-321 | Received 10 Jul 2020, Accepted 15 Sep 2020, Published online: 29 Jan 2021
 

Abstract

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

环境因素对犯罪行为决策有直接和间接的影响。本研究旨在探讨暴力犯罪的出现, 在多大程度上受到社会环境和建筑环境的空间影响。目前, 存在着一些用空间回归模型进行模拟犯罪率的研究, 但缺乏对空间回归模型的比较。特别的, 基于特征向量空间滤波的空间回归模型, 据报道已经有效地用于城市和区域研究, 但尚未广泛应用于犯罪数据。本文将探讨, 在空间暴力犯罪率模型领域, 基于空间滤波的空间回归模型是否优于传统的空间回归模型。此外, 基于日常活动理论, 本研究旨在探讨混合土地利用和街道连通性对暴力犯罪的影响。在实证研究中, 选取并评估了两种空间回归模型(空间误差模型、特征向量空间滤波模型), 本文成功地对美国纽约市局部暴力犯罪率进行了模拟。特征向量空间滤波模型优于空间误差模型和非空间模型。模型估计结果表明, 暴力犯罪(袭击和抢劫)的发生受到社会经济因素和建筑环境因素的影响。因此, 环境因素影响了暴力犯罪的发生。社会经济和建筑环境因素对暴力犯罪的影响, 为预防暴力犯罪的城市规划和政策制定提供了参考。特别的, 本研究为日常活动理论提供了新的证据, 即, 提高土地利用混合程度和街道连通性, 可以增加街道活动, 从而减少暴力犯罪的发生。为了继续增加街道活动, 政策制定者和城市规划者应加强土地利用混合度和街道连通性。此外, 特征向量空间滤波模型也可以用于城市和区域研究中的犯罪和其它应用。

Los factores ambientales tienen impactos tanto directos como indirectos en las tomas de decisiones relacionadas con conductas criminales. Este estudio se propuso examinar en qué grado puede ser afectada la ocurrencia de crímenes violentos por el entorno social y construido a través del espacio. Si bien unos pocos estudios han intentado modelar la tasa de criminalidad usando modelos de regresión espacial, es evidente la falta de comparación entre los modelos de regresión espacial. En particular, el tipo de eigenvector de filtrado espacial de los modelos de regresión espacial se reporta como efectivo en estudios urbanos y regionales, aunque no haya sido aplicado ampliamente a los datos sobre crimen. Nos propusimos examinar en este estudio si el tipo de filtrado espacial de los modelos de regresión espacial supera los tipos convencionales de modelos de regresión espacial para modelar las tasas de criminalidad violenta a través del espacio. Además, apuntamos a investigar los impactos del uso mixto de la tierra y la conectividad de calles sobre la ocurrencia de crímenes violentos según lo explicado por la teoría de actividad rutinaria. En estudios empíricos, se seleccionaron y calcularon con éxito dos tipos de modelos de regresión espacial (o sea, el modelo de error espacial y el modelo del eigenvector de filtrado espacial) para modelar tasas de criminalidad violenta a escala local, a través de la ciudad de Nueva York. Los modelos de eigenvector de filtrado espacial superan a los modelos de error espacial lo mismo que a los modelos no espaciales. Los resultados de la estimación de los modelos muestran que las ocurrencias de crímenes violentos (esto es, asaltos y robos) bien pueden achacarse a factores socioeconómicos y del entorno construido, y de ese modo los factores ambientales pueden afectar la ocurrencia de crímenes violentos. Las contribuciones de los factores socioeconómicos y del entorno construido al crimen violento pueden proporcionar perspicacias para la planificación urbana y la formulación de políticas relacionadas con prevención del crimen violento. Particularmente, este estudio ofrece nueva evidencia sobre la teoría de la actividad rutinaria en el sentido de que el incremento en el uso mixto del suelo y la conectividad de calles pueden aumentar la actividad callejera, reduciendo de ese modo las ocurrencias de crímenes violentos. Los legisladores y planificadores urbanos deben seguir incrementando la actividad en las calles por medio de un mayor uso mixto del suelo urbano y la conectividad de calles. Además, se propugna por el uso de modelos de eigenvector de filtrado espacial contra el crimen y otras aplicaciones de estudios urbanos y regionales.

Additional information

Notes on contributors

Yeran Sun

YERAN SUN is an Assistant Professor at the Department of Geography, College of Science, Swansea University, Swansea SA2 8PP, Wales, UK. E-mail: [email protected]. He is a GIScientist and human geographer with interests in urban informatics, urban big data, and sustainable cities.

Shaohua Wang

SHAOHUA WANG is a Postdoctoral Researcher at the CyberGIS Center for Advanced Digital and Spatial Studies, University of Illinois at Urbana–Champaign, Urbana, IL 61801. E-mail: [email protected]. He specializes in spatial optimization, spatial analysis, geoinformatics, and geographic information systems.

Jing Xie

JING XIE is a Postdoctoral Fellow at the Faculty of Architecture, The University of Hong Kong, China. E-mail: [email protected]. His research priorities include Earth observation, urbanization, vegetation ecology, and GIScience, specifically focusing on urban local climate zone, phenology and productivity of vegetation, mountainous ecosystems, land use and land cover, and climate change.

Xuke Hu

XUKE HU is a Postdoctoral Researcher at the Data Science Institute of German Aerospace Center (DLR), Mälzerstraβe 3, 07745 Jena, Germany. E-mail: [email protected]. His research interests are in the fields of indoor positioning, mapping, and navigation; volunteered geographic information; and social media data analysis. In particular, he is interested in using annotation-free deep learning techniques to solve the problems faced in Earth observation and disaster management.

Log in via your institution

Log in to Taylor & Francis Online

PDF download + Online access

  • 48 hours access to article PDF & online version
  • Article PDF can be downloaded
  • Article PDF can be printed
USD 53.00 Add to cart

Issue Purchase

  • 30 days online access to complete issue
  • Article PDFs can be downloaded
  • Article PDFs can be printed
USD 198.00 Add to cart

* Local tax will be added as applicable

Related Research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.