Robert Haining

University of Cambridge | Cam · Department of Geography

By deploying remotely sensed data together with spatial statistical modeling, we use regression modeling to investigate the relationship between the density of the built environment and two types of crime. We show how the Global Human Settlement Layer (GHSL) data set, which is a measure of building density generated from Sentinel 2A satellite image...

This study explored geospatial technologies currently used by various researchers, industries, health professionals, etc., in the fight against the global pandemic of COVID19. The use of dashboards is among the prominent innovative geospatial mapping technologies implemented by several bodies such as the Johns Hopkins University’s Center for System...

Spatial statistics is dominated by spatial autocorrelation (SAC) based Kriging and BHM, and spatial local heterogeneity based hotspots and geographical regression methods, appraised as the first and second laws of Geography (Tobler 1970; Goodchild 2004), respectively. Spatial stratified heterogeneity (SSH), the phenomena of a partition that within...

The chapter looks at the contribution Geographical Information Systems (GIS) have made to research into the spatial and temporal patterns of urban crime and criminality, indicating areas of possible growth in the future and sketching the policy relevance of these developments for practical policing and research. It discusses four main GIS empowered...

A review of the state of the art in spatial statistics for regional scientists, but relevant to social scientists generally, covering spatial econometric modelling and Hierarchical modelling with spatial dependence from a Bayesian perspective.

The objective of this article is to report the results of an ecological study into the geography of rape in Stockholm, Sweden using small area data. In order to test the importance of factors indicating opportunity, accessibility and anonymity to the understanding of the geography of rape, a two-stage modelling approach is implemented. First, the o...

The objective of this article is to report the results of an ecological study into the geography of rape in Stockholm, Sweden, using small area data. In order to test the importance of factors indicating opportunity, accessibility and anonymity to the understanding of the geography of rape, a two-stage modelling approach is implemented. First, the...

This paper estimates the parameters of the wage equation of the new economic geography (NEG) using a newly developed spatial panel model. The results show that wage rate variation across different prefectures in Japan can be explained by market potential, which is a key variable in NEG theory, while controlling for variation in labour efficiency. S...

The geography of crime and criminality is important in economic, political, and social geography, and there are several theoretical approaches. For acquisitive crime (e.g., theft and burglary), theories focus on the trade-off between risk and reward (rational choice) while emphasizing the importance of individual level and environmental factors. Ac...

This paper estimates the parameters of the wage equation of the new economic geography (NEG) using a newly developed spatial panel model. The results show that wage rate variation across different prefectures in Japan can be explained by market potential, which is a key variable in NEG theory, whilst controlling for variation in labour efficiency....

Notwithstanding long standing efforts to reduce the incidence of infectious diseases they continue to be a major cause of morbidity and premature death in many parts of the world. Part of the challenge is to understand better the factors that are associated with disease incidence at the local level and to put in place operational systems to achieve...

Spatial decision support systems have already proved their value in helping to reduce infectious diseases but to be effective they need to be designed to reflect local circumstances and local data availability. We report the first stage of a project to develop a spatial decision support system for infectious diseases for Karnataka State in India. T...

Public health and criminology have developed largely independently of one another at the research and policy levels so that the links between crime victimization and health status are not well understood. Although it is not difficult to support the idea of crime as a threat to the health of individuals and the wider community, the difficulty lies i...

Public health and criminology have developed largely independently of one another at the research and policy levels so that the links between crime victimization and health status are not well understood. Although it is not difficult to support the idea of crime as a threat to the health of individuals and the wider community, the difficulty lies i...

Handbook of Spatial Epidemiology explains how to model epidemiological problems and improve inference about disease etiology from a geographical perspective. Top epidemiologists, geographers, and statisticians share interdisciplinary viewpoints on analyzing spatial data and space-time variations in disease incidences. These analyses can provide imp...

The influence of hilliness on walking behavior could be a consequence of the real effect of the local topography, but individual perception of the difficulties associated with walking in a hilly environment may also be important. Previous studies have found that people's perceptions do not necessarily match well with the realities of walking in hil...

Spatial sampling is undertaken to estimate an attribute of a spatially distributed population. The attribute might relate to a quantity (how much) or to the distribution of values (where). Two models underlie spatial sampling, the design-based and model-based approaches, and these are described. A key issue with spatial sampling is selection of the...

Spatial autocorrelation is used to describe a particular form of spatial variation found in geographical data. Its presence is often indicative of something of interest in mapped data that requires explanation; may be used to tackle map interpolation problems; may raise statistical inferential problems because data are no longer independent. We dis...

Modelling spatio-temporal offence data contributes to our understanding of the spatio-temporal characteristics of the risk of becoming a victim of crime and has implications for policing. Space–time interactions are deeply embedded both empirically and theoretically into many areas of criminology. In this paper, we apply a familiar Bayesian spatio-...

We review some of the special properties of spatial data and the ways in which these have influenced developments in spatial data analysis. We adopt a historical perspective beginning in the early twentieth century before moving to the development of spatial autocorrelation statistics in geography’s Quantitative Revolution. Phases of development af...

Spatial sampling is widely used in environmental and social research. In this paper we consider the situation where instead of a single global estimate of the mean of an attribute for an area, estimates are required for each of many geographically defined reporting units (such as counties or grid cells) because their means cannot be assumed to be t...

Some police forces in the UK institute ‘No Cold Calling’ (NCC) zones to reduce cold callings (unsolicited visits to sell products or services), which are often associated with rogue trading and distraction burglary. This paper evaluates the NCC-targeted areas chosen in 2005–06 in Peterborough and reports whether they experienced a measurable impact...

About one decade has passed since US vice president Al Gore articulated his vision of Digital Earth DE. Within this decade, a global multi-resolution and three-dimensional 3D representation of the Earth, which sums up the DE vision, increasingly gained ...

The existing indicators related to spatial association, especially the K function, can measure only the same dimension of vector data, such as points, lines and polygons, respectively. We develop four new indicators that can analyze and model spatial association for the mixture of different dimensions of vector data, such as lines and points, point...

G eographical A nalysis ( GA ) , in cooperation with the W iley‐ B lackwell publishing business, undertook a project to complete the digitizing of all back issues of the journal and make those for the period 1969–2001 free to the academic community; the volumes for 2002–2005 already were, and continue to be, free. This article commemorates the comp...

Highly pathogenic avian influenza (HPAI) H5N1, a disease associated with high rates of mortality in infected human populations, poses a serious threat to public health in many parts of the world. This article reports findings from a study aimed at improving our understanding of the spatial pattern of the highly pathogenic avian influenza, H5N1, ris...

Test for spatial correspondence of H5N1 outbreaks and the empirical patterns. (TIF)

NJ tree of the 888 H5N1 concatenation of hemagglutinin (HA) and neuraminidase (NA) DNA sequences from East-Southeast Asia covering Thailand, Vietnam, Cambodia, Laos, Indonesia, and China. The best model is TVM+I+G (transversional model incorporating invariable sites and rate variation among sites). The goose H5N1 DNA sequence from Guangdong in 1996...

NJ trees for the H5N1 virus from (a) Thailand, (b) Vietnam, (c) Indonesia, and (d) China. The best model is GTR+I+G (General Time Reversible incorporating invariable sites and rate variation among sites. (TIF)

Illustration of the original and modified local K function. Note: the original local K function based on the number of outbreaks cannot distinguish between the cluster with the red and blue circles. The modified local K function, by taking into account the distance between outbreaks, is able to distinguish the two patterns. (TIF)

Dempster's combination for the three sources of evidence on H5N1 in Thailand. (PDF)

Spatial distribution of H5N1: spatial distribution of reported H5N1 outbreaks, inland water bodies, migratory bird pathways, pathways, and roads in East-Southeast Asia. (TIFF)

Logistic regression model assemssment for the H5N1 occurrences in East-Southeast Asia, Inodnesia, and China, 1996–2009 and the two epidemic waves between 1996–2004 and 2005–2009. (PDF)

ROC curves for the logistic regression model. The area under the ROC curve (AUC) indicates the probability of a correct classification. (a) and (b) show the average AUC of the models for outbreaks of East-Southeast Asia and Indonesia from 1996 to 2009. (c), (d), (e) are the AUC of the models for China for the periods between 1996 and 2009, 1996 and...

Results from phylogenetic tree analysis, modified local K function analysis, and logistic regression analysis for Indonesia, China, East-Southeast Asia. The values shown in the color bar are the probability of outbreaks of H5N1. (a), (d), (g) are the outcomes from the phylogenetic tree analysis (Figure 3(b) and Figures S3(c) and (d)), showing the s...

Spatial competition between firms is standard fare for traditional location theory and contemporary geographical economics. In this paper we examine the implications of modeling spatial competition using an approach grounded in geographical political economy, using mathematics as the language of theory. We make no presumptions about the existence o...

Ecological analysis, the statistical analysis of data aggregated by areas, has a long history in academic research into crime and disorder. The modern roots of this form of analysis date back to the Chicago School of Sociology in the 1920s and 1930s and from which social area analysis and factorial ecology grew after the Second World War. This work...

Georeferenced data or spatial data (we use the terms interchangeably here) come in many forms. Geometrically speaking, such data refer either to points, lines or areas – spatial objects or features. Spatial interaction data record flows between the nodes (intersection points) of a network. These data are captured in an origindestination matrix wher...

This paper considers the standard error of the estimate of the mean of a spatially correlated variable in the case where data are obtained by a process of random sampling. Two distinct mean estimation problems are identified: estimating the area mean and estimating the population mean. Methods are described for obtaining standard error estimates in...

This paper discusses methods of simulating two-dimensional surfaces that satisfy certain mathematical properties. Central to this discussion is the generation of surfaces that possess the property of spatial autocorrelation. The simulation of spatially autocorrelated surfaces has two primary objectives. The first objective is to generate surfaces w...

The paper examines the use of the Pearson product moment correlation coefficient and the Spearman rank correlation coefficient on map data that are spatially correlated. Research has shown that in this case standard estimators underestimate the true sampling variance of the Pearson coefficient. The Clifford and Richardson “effective sample size” so...

The problems of model specification in one- and two-dimensional stationary random fields are considered, with particular reference to the class of spatial autoregressions. The role of the autocorrelation function is discussed and it is shown to have a valuable exploratory use, especially in identifying directional bias in random fields. It is recom...

Two alternative specifications for random fields are reviewed and models from both specifications identified. The paper then deals with statistical tests for discriminating between randomness and some of the models of dependence. These various tests are compared and criteria established for their use. Additional testing procedures are identified fo...

Discusses a microeconomic or neighborhood approach to the specification of macroeconomic or regional price distributions. The region is assumed to consist of many markets, where each seller sets his prices with reference to the price levels set by local neighborhood sellers. The effects of local price sensitivity, the graph structure of interaction...

The class of mathematical interaction models for describing spatial configurations with dependence between site observations is introduced. After discussing their structure, the relationships between these models and geographical diffusion processes are dealt with. They appear to allow inclusion of the two properties of limited interaction and limi...

This paper considers the development of linked small-area spatial econometric models in which income flows between the areas constitute an important part of model specification. The attributes of income diffusion processes are considered in detail. Both static models and temporal income diffusion models are discussed. The spatial and spatial-tempor...

Maheswaran et al. (2006) analysed the effect of outdoor modelled NO(x) levels, classified into quintiles, on stroke mortality using a Poisson Bayesian hierarchical model with spatial random effects. An association was observed between higher levels of NO(x) and stroke mortality at the small area (enumeration district) level. As this model is framed...

One of the major sources of uncertainty associated with geographical data in GIS arises when they are the outcome of a sampling process. It is well known that when sampling from a spatially autocorrelated homogeneous surface, stratification reduces the error variance of the estimator of the population mean. In this study, we evaluate the efficiency...

Geostatistics is a distinctive methodology within the field of spatial statistics. In the past, it has been linked to particular problems (e.g., spatial interpolation by kriging) and types of spatial data (attributes defined on continuous space). It has been used more by physical than human geographers because of the nature of their types of data....

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 i...

This article reflects on the principal statistical methodological issues that quantitative geographers addressed in the 1950s and 1960s. The source of many of these methodological problems lies in the assumptions of classical statistics that data are independent and identically distributed. The correlation inherent in spatial data recorded at nearb...

Research into the impacts of crime on health is relevant to adopting effective social policy and encouraging partnerships between local health and crime prevention agencies. Although it is not difficult to support the notion of crime as a threat to public health, the difficulty lies in quantifying the impact. Confounding effects of other influentia...

The last few years has seen a steady growth in methodologies for displaying and analysing geographically referenced (spatial) data. Geographic Information Systems (GISs) and desktop mapping packages have provided the enabling technologies that have made some of these developments practical to implement within busy agencies. Spatial analysis techniq...

The problems arising when modelling counts of rare events observed in small geographical areas when overdispersion and residual spatial autocorrelation are present or anticipated are considered. Different models are presented for handling inference in this case. The different strategies are implemented using data on offender counts at the enumerati...

The 1990s saw the three Baltic states of Estonia, Latvia and Lithuania change from centrally planned to more market oriented economies with associated societal transformations. Profound changes such as these create uncertainty and social instability that can lead to social problems including increased rates of crime and disorder. We report and comm...

Proceedings from a Symposium, of the same name, held on the campus of Syracuse University from March to June, 1989. Chapters by the following authors: L. Anselin, P. Doreian, D. A. Griffith, R. P. Haining, K. V. Mardia, R. J. Martin, J. K. Ord, J. H. P. Paelinck, S. Richardson, B. D. Ripley, A. Sen, G. J. G. Upton, D. Wartenberg.

The paper investigates the location of serious crime neighbourhoods in Sheffield, England, in 1998 on the basis of two sources of data: senior police officer perceptions of where such neighbourhoods are and the evidence that is contained in the police's own database of recorded crime. We report the results of modelling these two spatial distributio...

Bayesian modelling of health risks in relation to environmental exposures offers advantages over conventional (non-Bayesian) modelling approaches. We report an example using research into whether, after controlling for different confounders, air pollution (NOx) has a significant effect on coronary heart disease mortality, estimating the relative ri...

The authors investigate geographical patterns of homicide in São Paulo, Brazil. The geography of crime in developing world cities has been an underresearched area in part because of the lack of good-quality, geocoded offence data. In the case of São Paulo the availability of a new digital police dataset has provided the opportunity to improve our u...

The importance of geographical information systems (GIS) for crime analysis, and strategic and tactical deployment of forces, has been increasingly recognized in both the United States and the United Kingdom. This was forcefully endorsed by former New York mayor, Rudolph Giuliani, during his visit to London in February 2002.

There is increasing evidence, mainly from daily time series studies, linking air pollution and stroke. Small area level geographical correlation studies offer another means of examining the air pollution-stroke association. Populations within small areas may be more homogeneous than those within larger areal units, and census-based socioeconomic in...

Supports both independent and interacting markets models, though at different intraurban scales. The nature of the interaction seems to be defined in terms of the principal routeways. Two further developments would be: a) investigation of price leader/price follower models and b) investigation of company level models. As a longer-term objective we...

Conditions for spatial price equilibrium are derived for a set of firms in oligopolistic spatial competition, distributed at fixed locations in a heterogeneous region where consumer purchasing patterns are a probabilistic function of the price distribution rather than a deterministic function of proximity to firms. The resulting prices vary with ac...

This paper describes statistics for model criticism in spatial econometrics. The purpose of these statistics is to evaluate how well a chosen model fits the data and to identify influential cases and how they affect the aggregate picture. The paper reviews results in Martin (1992) for the regression model with correlated errors where the coefficien...