Statistical Analysis of Spatial Crime Data

2012

Putting Crime in its Place, 2009

Social scientists have had a long and enduring interest in the geography of crime, and the explanation of variation of crime at place. In this introductory chapter we first describe the history of crime and place studies, showing that in the course of two centuries, scholars have increasingly focused their interest on smaller spatial units of analysis. In the 19th century they typically studied large administrative districts such as regions and countries. The Chicago School focused on much smaller urban communities. More recently, interest has moved towards geographic units as small as street blocks or addresses. After this historical account, we address specific questions regarding how the unit of analysis should be chosen for crime and place studies. We address substantive theoretical, statistical and practical problems that are raised in choosing appropriate levels of geography for research and practice. We discuss issues of theory and data and consider the factors that have inhibited the study of units of analysis of crime at place to date, mentioning the specific contributions to the unit of analysis problem that are made by the chapters that follow. Criminologists have had a long and enduring interest in the idea of place and its role in the production of crime (Weisburd and McEwen 1997). In 1829 Adriano Balbi and Andre-Michel Guerry compared education levels and crime across large French administrative areas ("departments") and discovered not only that crime varied across them, but that places with higher levels of education also had higher levels of property crime (Balbi and Guerry 1829; Kenwitz 1987). This finding though surprising at the time given popular assumptions about the role of poverty in crime, and reflective of a new fascination with the ability of social scientists to bring insights into the nature and causes of social problems, was reinforced in similar studies conducted during the period. For example, the Belgian astronomer and statistician Lambert Adolphe Quetelet (1831/1984) also observed the variability of crime across large administrative areas, noting that some

Statistica Neerlandica, 2003

Neighbourhood influence in criminology can be conceptualised both as pertaining to the influence of characteristics of a neighbourhood on its inhabitants, and to the mutual influence of characteristics of adjacent neighbourhoods on each other. The first conceptualisation asks for multilevel analysis, the second one for one of several spatial dependency (spatial autocorrelation) methods. Various models in both traditions are discussed and illustrated with data on victimisation and on burglary.

Journal of Quantitative Criminology, 2010

This essay offers a few reflections on cross-sectional criminological research about people in places where community-level causes are considered, and victimization or reactions to crime are the outcome. It is by design not only selective but also Janus-faced. On the one hand it notes accomplishments in this research area facilitated by increasing use of multilevel models. On the other hand it notes meta-theoretical challenges currently preventing work in this arena from advancing theoretically. Some of these concerns have been voiced by scholars in other disciplines (Entwisle 2007; Roux 2001, 2002, 2004). The discussion is pitched at a meta-theoretical level. That is, the focus is not on evaluating the specific merits of one theory versus another. Rather, comments center on concerns that cut across any number of theories. Using a Boudon-Coleman metamodel, relations between individuals and societal structure are highlighted (Boudon 1986: 29-31; Coleman 1990: 1-23). Because a significant impact of a community predictor in a multilevel model with an individual-level outcome is targeting ecological variation in the outcome, community-level variation in outcomes enters the discussion. Definitions and an Orienting Metamodel Of interest here are theories about the impacts of both community and individual features on individual-level outcomes like victimization, reactions to crime like fear or avoidance, or related perceptions of features of local context such as perceived risk. Relevant community features could be almost anything, depending on the theory: demographic structural dimensions, land use features, reported crime rates, removal or return rates, or features of local social, cultural or political climate. Communities are areas where people live which are smaller than cities and larger than individual address parcels or land uses (Hunter

2000

The new century brings with it growing interest in crime places. This interest spans theory from the perspective of understanding the etiol- ogy of crime, and practice from the perspective of developing effec- tive criminal justice interventions to reduce crime. We do not attempt a comprehensive treatment of the substantial body of theoretical and empirical research on place and crime

Journal of Criminal Justice Education, 2013

This article has four aims. First is to clarify the origins and different meanings of place, space, and other basic concepts in spatial analysis. The second aim is to reiterate the illogicality of the spatial homogeneity assumption in ordinary least squares (OLS) regression. An illustration of the comparison between traditional OLS and geographically weighted regression modeling is included for this purpose. The third aim is to explain that place matters in crime analysis not only when crime data are spatially clustered, but when relationships between correlates are found to be conditional upon place. The final aim is to convince criminology and criminal justice faculty to begin discussing the inclusion of spatial modeling as a compulsory topic in the curriculum.

Scientific Reports

Nowadays, 23% of the world population lives in multi-million cities. In these metropolises, criminal activity is much higher and violent than in either small cities or rural areas. thus, understanding what factors influence urban crime in big cities is a pressing need. Seminal studies analyse crime records through historical panel data or analysis of historical patterns combined with ecological factor and exploratory mapping. More recently, machine learning methods have provided informed crime prediction over time. However, previous studies have focused on a single city at a time, considering only a limited number of factors (such as socio-economical characteristics) and often at large in a single city. Hence, our understanding of the factors influencing crime across cultures and cities is very limited. Here we propose a Bayesian model to explore how violent and property crimes are related not only to socioeconomic factors but also to the built environmental (e.g. land use) and mobility characteristics of neighbourhoods. to that end, we analyse crime at small areas and integrate multiple open data sources with mobile phone traces to compare how the different factors correlate with crime in diverse cities, namely Boston, Bogotá, Los Angeles and Chicago. We find that the combined use of socioeconomic conditions, mobility information and physical characteristics of the neighbourhood effectively explain the emergence of crime, and improve the performance of the traditional approaches. However, we show that the socio-ecological factors of neighbourhoods relate to crime very differently from one city to another. Thus there is clearly no "one fits all" model. Criminology widely recognizes the importance of places 1,2 : crime occurs in small areas such as street segments, buildings or parks, and it is spatially stable over time 3,4. However, theoretical and empirical research showed that crime is also a consequence of socioeconomic contextual characteristics, usually referred to as the "neighbourhood effect" 5,6. In criminology, cooperation, as opposed to disorganization of neighbours, is indeed believed to create the mechanisms by which residents themselves achieve guardianship and public order 7 , solve common problems, and reduce violence 7-9. This mechanism also finds its roots in urban planning, where the relationship between specific aspects of urban architecture 10 and urban physical characteristics 11 are related to security. Places and neighbourhoods are not to be considered islands unto themselves, as they are embedded in a city-wide system of social interactions. On a daily basis, people's routine exposes residents to different conditions, possibilities 12 , and this routine may favour crime 13. Nevertheless, many empirical studies focus on just a subset of static factors at a time such as socioeconomic factors without considering the contextual built environment 8,9,14-17 , or ignoring mobility 15,16,18,19 , and often only drawing results in a single city (e.g. Chicago) 8,9,15,19-26. Studies on small areas and neighbourhoods roughly come from two streams of literature. The first stream focuses on the routine activity and crime pattern theories 13,27,28 at places. These studies suggest that crime occurs

1999

Crime maps are becoming significant tools in crime and justice. Advances in the areas of information technology, computing and Geographic Information Systems (GIS) have opened new opportunities for the use of (computerized) mapping in crime control and prevention programs. Crime maps are also valuable for the study of the ecology and the locational aspects of crime. Maps enable areas of unusually high or low concentration of crime to be visually identified. Maps are however only pictorial representations of the results of more or less complex spatial data analyses. This paper discusses the methodological problems with the spatial analysis of crime rates. The Poisson distribution is a natural candidate to model this type of data, but it has the problem that the variance is a function of the mean. In addition, rates in areas with small populations are more variable than in areas where populations are large. Moreover, data may exhibit spatial correlation, so a simple Poisson model fails to account for the whole variability in the underlying crime rates. As a consequence, maps based on crude crime rates and probability maps are misleading. A hierarchical model dealing with all these problems is proposed and applied to the regional analysis of firearm homicides in the Eastern Australian states. The analysis addresses the question of whether rural and non-rural areas differ in their associated risks of firearm-related homicide. It is shown that this risk is not associated with the rural character of an area, but with factors relating to social and economic disadvantage, which affect both rural and non-rural regions equally.

Journal of Environmental Systems, 1981

This paper identifies the development of theory and method in research pertaining to ecological aspects of delinquency and crime within urban areas. It is found that research effort in this field is focussed mainly on estimating the association between social area characteristics and delinquency and crime rates. It is suggested that incorporation of individual level determinants of delinquency and crime along with aggregate level properties of the area will enable us to derive the net effects of the area on occurrence of delinquency and crime. Hypotheses of this nature can be tested using the method of contextual analysis. This paper addresses the development of theory and method in research pertaining to ecological aspects of delinquency and crime. This area of research examines the spatial distribution of the levels of delinquency and crime among populations which have homogeneous social and cultural characteristics. The scope of this paper is confined to the methodological and theoretical aspects of the ecology of delinquency and crime within urban areas. The term delinquency and crime is taken to mean a large number of behaviors that violate legal norms [1]. EARLY STUDIES Many of the early studies on intra-urban variations in delinquency and crime stem from the Chicago school of human ecology. The most prominent among the early studies is that of Shaw and McKay [2], which examined the spatial distribution of male delinquents in Chicago. Shaw and McKay noted a few 101

Geographical Analysis, 2009

The purpose of this essay is to map out the dissemination of Cliff and Ord's 1969 work in the field of criminology. I argue that despite criminology's widespread application of geography, the full implications of the article have yet to be realized. First, the major types of spatial studies in criminology are outlined, followed by a depiction of the context of criminological research at the time the article was published. Next the major changes to the field occurring after the publication of Cliff and Ord's paper, focusing on technology advances and theory, are set out. I finish by highlighting what I believe is a missed opportunity in criminological research that requires closer attention to spatial autocorrelation.