Spatiotemporal Modeling of Correlated Small‐Area Outcomes: Analyzing the Shared and Type‐Specific Patterns of Crime and Disorder

This research applies a Bayesian multivariate modeling approach to analyze the spatiotemporal patterns of physical disorder, social disorder, property crime, and violent crime at the small‐area scale. Despite crime and disorder exhibiting similar spatiotemporal patterns, as hypothesized by broken windows and collective efficacy theories, past studies often analyze a single outcome and overlook the correlation structures between multiple crime and disorder types. Accounting for five covariates, the best‐fitting model partitions the residual risk of each crime and disorder type into one spatial shared component, one temporal shared component, and type‐specific spatial, temporal, and space–time components. The shared components capture the underlying spatial pattern and time trend common to all types of crime and disorder. Results show that population size, residential mobility, and the central business district are positively associated with all outcomes. The spatial shared component is found to explain the largest proportion of residual variability for all types of crime and disorder. Spatiotemporal hotspots of crime and disorder are examined to contextualize broken windows theory. Applications of multivariate spatiotemporal modeling with shared components to ecological crime theories and crime prevention policy are discussed.     

Persistence of Crime Hot Spots: An Ordered Probit Analysis

The temporal persistence of crime hot spots is recognized as a valuable indicator of consistent problem areas. The current literature has not adequately addressed the mechanisms that perpetuate or interrupt persistent crime hot spots. Investigating the persistence of violent crime hot spots in Columbus, Ohio, from 1994 to 2002, this study fills a gap in the literature by identifying neighborhood structural correlates that drive the persistence of hot spots. Specifically, this study identifies yearly crime hot spots, and estimates an ordered probit model to explore the neighborhood structural determinants. The results indicate that socio‐economic factors, identified from a synthesis of social disorganization theory and routine activity theory, significantly correlate with persistent patterns of violent crime hot spots. This gives evidence that a combination of the two ruling spatial theories of crime provides an applicable framework for understanding the temporal dimension of violent crime hot spots. By identifying the factors that contribute to the persistence of hot spots of crime, insights gained from the results can help to inform focused crime prevention efforts.     

Crime Risk Maps: A Multivariate Spatial Analysis of Crime Data

In crime analyses, maps showing the degree of risk help police departments to make decisions on operational matters, such as where to patrol or how to deploy police officers. This study statistically models spatial crime data for multiple crime types in order to produce joint crime risk maps. To effectively model and map the spatial crime data, we consider two important characteristics of crime occurrences: the spatial dependence between sites, and the dependence between multiple crime types. We reflect both characteristics in the model simultaneously using a generalized multivariate conditional autoregressive model. As a real‐data application, we examine the number of incidents of vehicle theft, larceny, and burglary in 83 census tracts of San Francisco in 2010. Then, we employ a Bayesian approach using a Markov chain Monte Carlo method to estimate the model parameters. Based on the results, we detect the crime hotspots, thus demonstrating the advantage of using a multivariate spatial analysis for crime data.     

A Spatiotemporal Bayesian Hierarchical Approach to Investigating Patterns of Confidence in the Police at the Neighborhood Level

Public confidence in the police is crucial to effective policing. Improving understanding of public confidence at the local level will better enable the police to conduct proactive confidence interventions to meet the concerns of local communities. Conventional approaches do not consider that public confidence varies across geographic space as well as in time. Neighborhood level approaches to modeling public confidence in the police are hampered by the small number problem and the resulting instability in the estimates and uncertainty in the results. This research illustrates a spatiotemporal Bayesian approach for estimating and forecasting public confidence at the neighborhood level and we use it to examine trends in public confidence in the police in London, UK, for Q2 2006 to Q3 2013. Our approach overcomes the limitations of the small number problem and specifically, we investigate the effect of the spatiotemporal representation structure chosen on the estimates of public confidence produced. We then investigate the use of the model for forecasting by producing one‐step ahead forecasts of the final third of the time series. The results are compared with the forecasts from traditional time‐series forecasting methods like naïve, exponential smoothing, ARIMA, STARIMA, and others. A model with spatially structured and unstructured random effects as well as a normally distributed spatiotemporal interaction term was the most parsimonious and produced the most realistic estimates. It also provided the best forecasts at the London‐wide, Borough, and neighborhood level.     

A Bayesian Approach to Modeling Binary Data: The Case of High‐Intensity Crime Areas

This paper reports the fitting of a number of Bayesian logistic models with spatially structured or/and unstructured random effects to binary data with the purpose of explaining the distribution of high‐intensity crime areas (HIAs) in the city of Sheffield, England. Bayesian approaches to spatial modeling are attracting considerable interest at the present time. This is because of the availability of rigorously tested software for fitting a certain class of spatial models. This paper considers issues associated with the specification, estimation, and validation, including sensitivity analysis, of spatial models using the WinBUGS software. It pays particular attention to the visualization of results. We discuss a map decomposition strategy and an approach that examines properties of the full posterior distribution. The Bayesian spatial model reported provides some interesting insights into the different factors underlying the existence of the three police‐defined HIAs in Sheffield.     

The homicidal nation: An investigation into violence in the United States

Violent crime occupies a central place in American political culture, both as an element of the national character and as the focus of continuing policy debates on issues as disparate as school integration and gun control. This paper seeks to identify the root of the American penchant for violent crime, and for homicide in particular, and sketches its political implications. An “opportunity” model, stressing reaction to social immobility in a society with pervasive achievement‐oriented symbols, provides an appealing approach. It fails to explain, however, the regional violence characterising the South. Institutional factors, notably the weaknesses in a fragmented, locally‐controlled system of law enforcement within a non‐parliamentary democracy, must also contribute to this American problem.     

Crime Exposure Along My Way Home: Estimating Crime Risk Along Personal Trajectory by Visual Analytics

Crime has been one of the notorious public threats in cities. Fortunately, the increasing digital crime data provide great opportunities to analyze and control crime incidents. However, studies that predict the risk of crime exposure for an individual’s spatiotemporal paths based on historical crime big data are still limited. In this study, we have proposed the crime risk index (CRI) for spatiotemporal trajectory and built a model to estimate the CRI. Furthermore, an online crime risk analysis platform has been developed based on the model. First, we proposed a multi-scale tile system and a novel algorithm to estimate trajectory-based CRI using big historical crime data and entropy-based weighting. Second, we created a web-based platform that allows users to provide a spatiotemporal trajectory and estimate the crime risk for such trajectory. We conducted several experiments based on the crime data in Detroit. Results demonstrate the practicability and generalizability of our platform. The proposed model and platform can be applied to multiple cities, providing useful references for crime information and public safety.     

Applying Geostatistical Analysis to Crime Data: Car-Related Thefts in the Baltic States

Geostatistical methods have rarely been applied to area-level offense data. This article demonstrates their potential for improving the interpretation and understanding of crime patterns using previously analyzed data about car-related thefts for Estonia, Latvia, and Lithuania in 2000. The variogram is used to inform about the scales of variation in offense, social, and economic data. Area-to-area and area-to-point Poisson kriging are used to filter the noise caused by the small number problem. The latter is also used to produce continuous maps of the estimated crime risk (expected number of crimes per 10,000 habitants), thereby reducing the visual bias of large spatial units. In seeking to detect the most likely crime clusters, the uncertainty attached to crime risk estimates is handled through a local cluster analysis using stochastic simulation. Factorial kriging analysis is used to estimate the local- and regional-scale spatial components of the crime risk and explanatory variables. Then regression modeling is used to determine which factors are associated with the risk of car-related theft at different scales.     

The sociospatial ecology of deaths during police interactions in the United States, 2016–2020

Who dies in police custody? Where? To answer these questions, we use spatially disaggregated georeferenced data that measure 9098 deaths occurring by multiple causes during interactions with police throughout the U.S. from 2016 to 2020. We use a Sociospatial Ecology framework and Bayesian statistics over U.S. counties that establishes the relationship between social contexts – regional poverty, White/non-White population, violent crime rates, and political identity – and the risk of dying during police interactions. In addition, we evaluate the effects of police force Whiteness on deaths during police interactions. Controlling for alternative explanations, we show heterogeneous distributions of fatality risk, with large clusters in the Southwest and isolated high-probability pockets in other states. Risk maps allowing for visualization of these patterns are provided. We arrive at five main results. 1) There is a general trend of higher death during police interaction in areas of high poverty, fewer White people, higher violent crime rates, and higher populations with conservative values. 2) A great risk of deadly encounters for Black people exists throughout most of the U.S., while regional patterns of high risk exist for all other people of color. 3) White deaths during police interactions are most sensitive to ecological factors. 4) The risk of Blacks getting killed by police increases in White areas regardless of violent crime rates. 5) Higher proportions of White police within U.S. counties leads to higher interactive death risk for all races/ethnicities except Asian/Pacific Islander. Ultimately, our findings identify widespread racial/ethnic biases in situations of power and control.     

Broken Windows Policing and Constructions of Space and Crime: Flatbush,Brooklyn

While broken windows policing has triggered explosive debates about law enforcement and racism across US cities, it has maintained considerable support by racialized urbanites. Focusing on Flatbush, Brooklyn, this paper seeks to understand the striking resilience of broken windows in inner‐city contexts. It uses Laclau and Mouffe's discourse theory to analyze dialogue at Precinct Community Council meetings and interviews with attendees. The paper makes the case that the New York Police Department normalizes broken windows through discursive constructions of social space and crime that naturalize the precinct scale, produce spatial meanings, and cast social difference in the mold of broken windows theory. The article illustrates beyond the politics of racialized fearmongering, the normalization of broken windows also occurs through this meticulous production of geographic knowledge. It also emphasizes that deconstructing the way the police portray space and crime provides signposts for substantive reform to broken windows.     

IS CRIME BAD FOR BUSINESS? CRIME AND COMMERCIAL PROPERTY VALUES IN NEW YORK CITY

To test how crime affects economic activity, we use point‐specific data on crime, commercial property sales and assessed values from New York City, relying on an instrumental variables strategy. We find that crime reduces commercial property values, and the magnitude of the effect depends on the type and geography of crime. Elasticities range from ?0.1 to ?0.5. We find stronger evidence for negative violent crime effects in neighborhoods with lower incomes and higher shares of minority residents. Thus, disadvantaged neighborhoods are doubly harmed by crime—they have higher crime rates and those crimes have stronger effects on economic activity.     

Has it become warmer in Alberta? Mapping temperature changes for the period 1950–2010 across Alberta,Canada

When a Canada‐wide daily climate time series, covering the period 1950–2010, became available, an opportunity arose to analyze the time series for trends of a variety of temperature indices. The 6,833 climate grid cells covering Alberta, each with an area of 10 km by 10 km, allowed the detailed mapping of 30 temperature indices across the province. From each time series, an annual series was computed, which then enabled trend analyses using the non‐parametric Mann‐Kendall and Sen Slope tests. New maps could be created at an unprecedented spatial resolution, and an associated website was developed to access all trends and changes between 1950 and 2010 for all grid cells at albertaclimaterecords.com . The confidence levels of some temperature trends exceed 99%, while others are below 80%. In Alberta's south, annual average temperatures have increased by 1°C to 2°C since the 1950s, but in Alberta's north the increase is 2°C to 4°C. The growing season has lengthened by between one and five weeks since the 1950s, while the number of frost days has declined. The most significant trends observed were increases in mean annual and winter temperatures, and declines in the number of days below ?20°C and heating degree days.     

国外交通地理学研究的知识图谱与进展

交通地理学作为人文地理学的重要分支,一直充满着活力与多样性,获得人文地理学者的广泛关注。本文基于CiteSpace可视化软件,采用Web of Science中收录1982-2014年的4840篇交通地理学论文作为原始数据,梳理了近30年的研究脉络,绘制了学科发展的知识图谱,系统地归纳了学科的研究热点与发展趋势,以期为中国交通地理学研究提供借鉴。研究发现:国外交通地理学研究方法和研究内容日趋多元化,研究视角趋向微观化,质性研究突显;初步形成城市规划学派、理论地理学派、时间地理学派等六大学术共同体;出现社会、行为、文化和流动的诸多转向,呈现出人本导向、信息导向和交叉化的发展趋势。     

Moral Panic and Cultural Mobilization: Responses to Transition,Crime and HIV/AIDS in KwaZulu‐Natal

This article discusses the micropolitics behind the murder of an ANC councillor in a KwaZulu‐Natal slum area in 1999, and the forms of violence which have continued in the aftermath of apartheid. The history of violence is traced back to struggles between the IFP and the ANC in the 1980s which interacted with differences in generational, moral and cultural outlook, as well as with conflicts between Zulu‐speaking residents and immigrants from the Transkei. Since apartheid was dismantled, similar patterns of conflict have persisted, but now within a local context in which one political party holds almost total sway. Post‐apartheid violence is related to rivalries around local state resources in a situation of continued poverty, and to moral and ideological disagreements which, since 1994, have been intensified by the HIV/AIDS epidemic as well as by an escalation of local crime. Strategies for the moral rehabilitation of local society, such as virginity testing, are discussed, as is the controversy around them, rooted in oppositions between youth and elders, and between different cultural styles. Finally, the mismatch between the concentration of political power at municipal ward level and the diversity of positions expressed in local civil society is raised as a reason why disagreements have continued to involve violent conflict.     

Spatial Autocorrelation Statistics of Areal Prevalence Rates under High Uncertainty in Denominator Data

We propose a new estimator of spatial autocorrelation of areal incidence or prevalence rates in small areas, such as crime and health indicators, for correcting spatially heterogeneous sampling errors in denominator data. The approach is dubbed the heteroscedasticity‐consistent empirical Bayes (HC‐EB) method. As American Community Survey (ACS) data have been released to the public for small census geographies, small‐area estimates now form the demographic landscape of neighborhoods. Meanwhile, there is growing awareness of the diminished statistical validity of global and local Moran’s I when such small‐area estimates are used in denominator data. Using teen birth rates by census tracts in Mecklenburg County, North Carolina, we present comparisons of conventional and new HC‐EB estimates of Global and Local Moran’s I statistics created on ACS data, along with estimates on ground truth values from the 2010 decennial census. Results show that the new adjustment method dramatically enhances the statistical validity of global and local spatial autocorrelation statistics.     

基于道路网络的犯罪空间聚集特征研究

由于目前犯罪空间聚集特征研究的单元主要是地点、街区、巡逻区等,但是许多警务工作是沿道路网络开展的,因此有必要研究犯罪在道路网络上的空间聚集特征。本文以路段为分析单元对浙江省某地2011-2014年发生的16787起盗窃类犯罪进行了研究。通过分析,发现:1在道路网络中存在犯罪热点路段;2犯罪在路段上具有聚集性,少部分犯罪热点路段聚集了大部分犯罪,如19.86%的犯罪热点路段聚集了53.42%的犯罪;3犯罪热点路段在道路网络中也具有空间聚集性,主要聚集在类型为住宅区、大学、商业区等7个区域。根据犯罪在道路网络上的聚集特征,警察部门能优化相关警务工作,科学分配警力资源,从而提高治安防控、犯罪预防、侦查破案等能力和效率。     

Age changes in bone microstructure: do they occur uniformly?

Age estimations based on conventional multifactorial methods were compared with trends observed in the internal morphology of bones obtained from high‐resolution µCT. Specifically, average trabecular thickness and number of trabeculae/mm transect were determined in the non‐load‐bearing capitate (hand) and the load‐bearing navicular (foot). The µCT findings reveal age‐related trends but—surprisingly—these correspond only loosely with the ages assigned by conventional ageing methods, and are also not in accordance with what would be predicted from biomechanical considerations: trabeculae tend to be thinner in the (habitually) load‐bearing navicular than in the (habitually) non‐load‐bearing capitate. While the statistically significant correlation between trabecular thickness and number of trabeculae would suggest a compensatory mechanism between these two aspects of microanatomy, they are not correlated with the assigned ages and, importantly, may differ between sexes. Only in females is there an unequivocal trend towards trabecular thickness increase with age. These findings, although unexpected, can be reconciled with recent histological evidence and assumed average activity levels in historical populations. Conversely, changes in trabecular number are less clear‐cut and may be due to the lack of very old individuals in the sample. Nevertheless, the trends observed for trabecular thickness, as well as for trabecular number, seem to imply that the higher incidence of osteoporosis in women could be explained from a structural point of view alone. Copyright © 2005 John Wiley & Sons, Ltd.     

国外旅游犯罪研究综述

旅游犯罪作为一个严重的社会问题,近年来引起了社会各界的广泛关注,并成为国外旅游研究的重要领域之一。本文在梳理国外相关文献的基础上,对旅游与犯罪的关系、旅游犯罪的形成原因、时空分布规律、分类专项研究、旅游者与居民对犯罪的感知、相关社会影响和防范治理等多个方面进行了较详细的分析,以期能为国内旅游犯罪的防治和相关研究提供有益的思路和借鉴。     

Governing childhood through crime prevention: the case of the German school system

Over the last decade, numerous crime prevention programmes have been implemented across the German school sector. Although several serious violent attacks have happened in the last 12 years in German schools, the emergence of crime prevention programmes within the education sector cannot simply be conceived as a reaction to a rise in youth crime. Following Michel Foucault's writings on power and governmentality, and drawing upon extracts of a discourse analysis of crime prevention programmes and political speeches, we argue that crime prevention within German schools signifies a new mode of governing childhood. Although we focus on Germany, our findings may illustrate an international trend within education policy, which first tends to spatialise socio-structural problems and transform them into local solutions, and second seeks to create childhood subjectivities that cause children to feel responsible for their own safety, while simultaneously subjecting children and young people to wide-ranging social control via area-based networks.     

Single and Multiscale Models of Process Spatial Heterogeneity

Recent work in local spatial modeling has affirmed and broadened interest in multivariate local spatial analysis. Two broad approaches have emerged: Geographically Weighted Regression (GWR) which follows a frequentist perspective and Bayesian Spatially Varying Coefficients models. Although several comparisons between the two approaches exist, recent developments, particularly in GWR, mean that these are incomplete and missing some important axes of comparison. Consequently, there is a need for a more thorough comparison of the two families of local estimators, including recent developments in multiscale variants and their relative performance under controlled conditions. We find that while both types of local models generally perform similarly on a series of criteria, some interesting and important differences exist.