Spatial autocorrelation

Long-term modeling of agricultural land use is central in global scale assessments of climate change, food security, biodiversity, and climate adaptation and mitigation policies. We present a global-scale dynamic land use allocation model and show that it can reproduce the broad spatial features of the past 100 years of evolution of cropland and pastureland patterns. The modeling approach integrates economic theory, observed land use history, and data on both socioeconomic and biophysical determinants of land use change, and estimates relationships using long-term historical data, thereby making it suitable for long-term projections. The underlying economic motivation is maximization of expected profits by landowners within each grid cell. The model predicts fractional land use for cropland and pastureland within each grid cell based on socioeconomic and biophysical driving factors that change with time. The model explicitly incorporates the following key features: (1) land use competition, (2) spatial heterogeneity in the nature of driving factors across geographic regions, (3) spatial heterogeneity in the relative importance of driving factors and previous land use patterns in determining land use allocation, and (4) spatial and temporal autocorrelation in land use patterns.

We show that land use allocation approaches based solely on previous land use history (but disregarding the impact of driving factors), or those accounting for both land use history and driving factors by mechanistically fitting models for the spatial processes of land use change do not reproduce well long-term historical land use patterns. With an example application to the terrestrial carbon cycle, we show that such inaccuracies in land use allocation can translate into significant implications for global environmental assessments. The modeling approach and its evaluation provide an example that can be useful to the land use, Integrated Assessment, and the Earth system modeling communities.

In the first part of this chapter we provide a brief overview of the range of different ecological theories that have been advanced to explain the link between socially disadvantaged neighbourhoods and levels of crime and perceptions of (or fear of) crime. In the second part of the chapter we consider the two main weaknesses of neighbourhood effect studies – definition of neighbourhood and selection bias – and we demonstrate, by way of empirical example, how understanding of the ways in which neighbourhoods affect local residents can be further extended by allowing for the additional influences of surrounding local areas, using data from the British Crime Survey. This draws upon methodological work incorporating spatial autocorrelation in neighbourhood  models (see for example Morenoff et al., 2001). In the third and final part of the chapter, we discuss the extent to which this range of neighbourhood effects research has influenced policing and crime reduction policy initiatives in England and Wales. Here we discuss the growing importance that neighbourhoods and local communities have held in policy strategies to reduce crime and raise public confidence. We highlight a number of initiatives including neighbourhood watch, neighbourhood policing, new deals for communities, community wardens (latterly Police Community Support Officers) and crime and disorder reduction partnerships.

This paper analyses the special features that
characterise the spatial structure of Central and
Eastern Europe, a region still in the phase of
transformation. This topic has already been
discussed by numerous authors (Gorzelak 1997,
Rechnitzer et al. 2008); the corresponding studies
have identified both greater and lesser developed
areas, as well as other intermediate areas, leading
to various ‘geodesigns’, figures, and models. First,
a brief description of the main studies of spatial
structure affecting the macroregion is given; then
our definition of the spatial structure of Central
and Eastern Europe is outlined. This is not only
based on the main traditional development
indicators (e.g. GDP per capita, unemployment
rate, and business density), but also considers the
spatial structure layers (economy, society,
concentration, settlement pattern, network, and
innovation).
Introduction

The combined use of remote sensing based land cover classification and landscape metrics has provided a positive step toward gaining a comprehensive understanding of the features of landscape structure. However, numerous limitations of land cover classification indicate that the utilization of classified thematic maps in landscape pattern analysis is questionable and may even lead to large errors in subsequent analyses. Instead of generating and employing detailed land cover classification maps, the utility of local spatial autocorrelation indices derived directly from satellite imagery to measure landscape fragmentation was examined. Since local spatial autocorrelation can capture spatial pattern at a local scale, it can be expected to detail the spatial heterogeneity for various parts of a landscape instead of providing a single value as in the case with the global measures. This study compares the traditional landscape metrics to the use of satellite imagery based local spatial autocorrelation measures in quantifying landscape structure over Phoenix urban area. Two local spatial autocorrelation indices, the Getis statistic and the local Moran's I were employed in evaluating landscape pattern, using normalized indices as the inputs. Results show that there is a clear relationship between local spatial autocorrelation indices and FRAGSTATS metrics. Both the Getis statistic and the local Moran's I can serve as useful indicators of landscape heterogeneity, for the entire landscape, and for different land use and land cover types. The paper provides a feasible methodology for urban planners and resource managers for effectively characterizing landscape fragmentation using continuous dataset.

This paper presents a set of tools of exploratory spatial data analysis (ESDA) existent in SPRING. These tools increase the capacity of extraction of additional information of the spatial data, making possible the analyst to understand the dynamics spatial present in your study. The tools are based on the concept of spatial autocorrelation, being applicable to area data, spatial objects

The approach taken in this paper, namely synthesising a wealth of previous information with new data and a genetic model, in combination with integrated numerical analyses, led to new insights into the geological controls on the localisation of auriferous veins and residual prospectivity of the Charters Towers goldfield, NE Australia. The method also has implications for the assessment of other "mature" goldfields worldwide.

Transit oriented design (TOD) – an increase in density around transit stations - has arisen in many of Australia’s capital cities as a way to encourage mass transit ridership as well as to efficiently utilise the increase in foot and vehicle traffic that transit stations create. However, the implementation of TODs in Melbourne has faced strong opposition due to residents’ perception that the disamenities of a TOD will outweigh the benefits resulting in negative impacts on property prices. This research analyses the relationship between proximity to a TOD and residential home prices.  Results indicate that proximity to a TOD is positively related to property prices, even after controlling for neighborhood factors such as street connectivity and overall land use mix.  By testing a variety of transformations of distance, we find that the benefits of TOD proximity extend approximately 1250 meters from the Box Hill station.  From a methodological standpoint, we find that more flexible treatments of distance variables in spatial autoregressive and spline models produce better model fit and lead to results more in line with urban economic theory.

Contrary to expectations from either human capital or gender empowerment perspectives, analyses across 409 Indian districts show that girls have relatively lower literacy compared to boys in areas where more women are in the labor force. The most likely explanation is that areas with higher women's labor force participation are also areas with higher girls' labor force participation; these higher rates of girls' labor depress their literacy and education. Gender inequalities in literacy are therefore an exception to the usual egalitarian impacts of women's labor force participation and remind us again of the multidimensionality of gender inequalities.

Transaction activities at Jetwash Auto Spa are still recorded manually. In service transactions, customer acceptance only relies on manual transaction evidence, it makes the output format is not standardized. Therefore, sometimes it can effect lost documents. The stock of goods in car salons is only recorded in some books so that it can not be controlled, such as how many the amount of goods available and that is exhausted, otherwise it is difficult to adjust the price of goods with market prices is also a constraint due to the absence of price history of goods. Then, with the design analysis Jetwash Auto Spa application Tangerang web-based it becomes easier to do data collection.

A goal of landscape ecology is to infer processes or constraints that generate spatial pattern in communities and ecosystems. The rich tradition of plant community ecology is now being extended to address spatial pattern in vegetation over large spatial extents. The challenge in this is that vegetation pattern on landscapes is fine-grained, which presents sampling problems for large study areas. Further, spatial autocorrelation in ecological data, coupled with strong patterns of correlation among environmental factors (such as the gradient complexes governed by elevation) make it difficult to make clear inferences about the agents patterning landscape-scale vegetation. Here we review the methods of plant community ecology as extended to landscapes, and illustrate the challenges with a case study from Sequoia-Kings Canyon National Park in California's southern Sierra Nevada. We outline an iterative approach to such studies, with three stages. The first stage is a pilot study to characterize the spatial scaling of environmental factors presumed to be important to vegetation; this stage can often be conducted virtually, using digital terrain data. The second stage is iterative, and consists of building a preliminary explanatory model using a combination of ordination, classification, and Mantel tests-all analyses based on the same ecological distance or dissimilarity matrices. This preliminary model is then attacked to find its uncertain or sensitive parts, and these parametric conditions are mapped into geographic space to identify candidate sites for follow-up field studies in the third stage. This approach ensures that the most uncertain aspects of the preliminary model are refined in an efficient manner. As the approach proceeds toward a richer understanding of species-environment relationships and vegetation pattern, a need emerges for new kinds of field studies and novel extensions to existing statistical analyses. We discuss possible extensions of these as a natural consequence of this iterative process of model construction and revision.

Where you live seems to shape your worry about crime. Structural characteristics of neighbourhoods, visual signs of disorder and recorded crime have all been shown to have a direct and independent effect on individual levels of fear of crime. But when individuals evaluate their personal risk of crime, do they draw on the wider social and physical environment that extends beyond their own neighbourhood’s boundaries? Does – in short – the wider urban fabric matter? In this chapter we link individual survey data (from a national probability sample of individuals resident in urban areas of England and Wales) to independent measures of neighborhood demographic characteristics, visual signs of disorder, and reported crime. Testing so-called ‘spatial autocorrelation’, our findings indicate geographical spill-over effects. Living near an area with high crime rate and visible signs of low level disorder is associated with a higher probability of worrying about crime, even holding constant one’s immediate neighbourhood context. People’s conceptions of their neighbourhood may be more complex than standard administrative boundaries, with people’s routine activities often taking them further than their own immediate locality. Equally, individuals may also assume that the crime and disorder that occurs ‘next door’ can intrude on their own ‘doorstep.’

The spatial heterogeneity of populations and communities plays a central role in many ecological theories, for instance the theories of succession, adaptation, maintenance of species diversity, community stability, competition, predator-prey interactions, parasitism, epidemics and other natural catastrophes, ergoclines, and so on. This paper will review how the spatial structure of biological populations and communities can be studied. We first demonstrate that many of the basic statistical methods used in ecological studies are impaired by autocorrelated data. Most if not all environmental data fall in this category. We will look briefly at ways of performing valid statistical tests in the presence of spatial autocorrelation. Methods now available for analysing the spatial structure of biological populations are described, and illustrated by vegetation data. These include various methods to test for the presence of spatial autocorrelation in the data: univariate methods (all-directional and two-dimensional spatial correlograms, and two-dimensional spectral analysis), and the multivariate Mantel test and Mantel correlogram; other descriptive methods of spatial structure: the univariate variogram, and the multivariate methods of clustering with spatial contiguity constraint; the partial Mantel test, presented here as a way of studying causal models that include space as an explanatory variable; and finally, various methods for mapping ecological variables and producing either univariate maps (interpolation, trend surface analysis, kriging) or maps of truly multivariate data (produced by constrained clustering). A table shows the methods classified in terms of the ecological questions they allow to resolve. Reference is made to available computer programs.

The study explores whether small-scale species diversity, species evenness and species richness in semi-natural grassland communities are similarly associated with present management regime and/or present and historical landscape context (percentage of different land-cover types in the surroundings). Species diversity, evenness and richness were recorded within 441 50 × 50 cm grassland plots in 4.5 × 4.5 km agricultural landscape on Öland, Sweden. Recent and historical land-cover maps (years 2004, 1959, 1938, 1835, and 1800) were used to characterize the present and past landscape context of the sampled vegetation plots. Partial regression and simultaneous autoregressive models were used to explore the relationships between species diversity measures (Shannon diversity, richness and evenness) and different explanatory variables while accounting for spatial autocorrelation in the data. The results indicated that species richness was relatively sensitive to grassland isolation, while the response of species evenness to isolation was characterized by a degree of inertia. Because the richness and evenness components of species diversity may respond differently to habitat fragmentation, we suggest that monitoring projects and empirical studies that focus on changes in biodiversity in semi-natural grasslands should include the assessment of species evenness – as a complement to the assessment of species richness. In addition, our results indicated that the development and persistence of a species-rich and even grassland vegetation was favoured in areas that have historically (in the 19th century) been surrounded by grasslands. Information on landscape history should, whenever possible, be incorporated into the planning of strategies for grassland conservation.

Development of suitable approaches to the analysis of genetic diversity in a spatial context, where factors such as pollination, seed dispersal, breeding system, habitat heterogeneity and human influence are appropriately integrated, can provide new insights in the understanding of the mechanisms of maintenance and dynamics of populations. In this sense, it is important to recognise that patterns and processes may take place at different scales at the same time, and that the scales of a study must be chosen in accordance with the objectives pursued. Apart from conventional approaches to genetic structure, spatial autocorrelation and related techniques, such as Mantel test, correlograms, Mantel correlograms, join-counts, variograms and point pattern analysis, can detect and characterise the existence of spatial genetic structures and lead the way to discussing the environmental and biological factors responsible for them. An alternative way of including spatial variability in modelling approaches that deal with genetic patterns or processes is through the use of constrained ordinations. Although scarcely used at present, these methodologies have great applicability in conservation biology and can lead a way to an effective integration of genetic, demographic and ecological perspectives. #

This paper investigates directional influences in the distribution of Bronze Age surface pottery in the northern Murghab Delta, Turkmenistan. Drawing upon a continuous dataset of pottery sherd counts obtained by intensive field survey, it examines the degree to which we can make sense of the archaeological processes at work in a heavily obstructed and dynamic landscape. In so doing, it makes use of two analytical methods that have rarely been used in archaeology: a) geostatistical analysis using variograms to investigate directional spatial autocorrelation in recorded sherd counts; and b) angular wavelet analysis in evaluating directional influences in the sherd distributions for particular chronological periods. While some kinds of directional influence can be identified visually, a quantitative approach is particularly useful in deconstructing such patterns. In this particular dataset, distinct but related directional processes can be identified and measured: a) the impact of the complex system of watercourses in the delta on both settlement and post-depositional processes; and b) recovery bias in the observations made during survey.

How can spatial location affect the operation of society, population or economic conditions? What is the role of neighbourhood and distance in social phenomena? In what way can a social organisation limit spatial barriers? How would spatial structures be affected by the attraction and repulsion of territorial units? Does society only use or also design regions? These questions are explored in this study.
This work analyses some important issues, concepts and analysis procedures of the territorial structure of society and social processes of spatiality. It does not contain a comprehensive theory of spatiality and regional science; it is primarily a practical empirical research.
Many theoretical works aim at defining the spatial structure of Europe. This article provides an overview of models describing the spatial structure of Europe. The study describes the economic spatial structure of Europe using bi-dimensional regression analysis, based on the gravity model. The spatial structure of Europe is illustrated with the help of the gravity model and spatial auto-correlation. With these patterns, it is possible to justify the appropriateness of the models based on different methodological backgrounds by comparing them with the results of this paper.
The subject of field theory concepts and methods that can aid regional analyses is examined, and attempts to offer a synthesised knowledge with a wide variety of examples and methods.

Eigenvector-mapping methods such as Moran's eigenvector maps (MEM) are derived from a spatial weighting matrix (SWM) that describes the relations among a set of sampled sites. The specification of the SWM is a crucial step, but the SWM is generally chosen arbitrarily, regardless of the sampling design characteristics. Here, we compare the statistical performances of different types of SWMs (distance-based or graph-based) in contrasted realistic simulation scenarios. Then, we present an optimization method and evaluate its performances compared to the arbitrary choice of the most-widely used distance-based SWM. Results showed that the distance-based SWMs generally had lower power and accuracy than other specifications, and strongly underestimated spatial signals. The optimization method, using a correction procedure for multiple tests, had a correct type I error rate, and had higher power and accuracy than an arbitrary choice of the SWM. Nevertheless, the power decreased when too many SWMs were compared, resulting in a trade-off between the gain of accuracy and the loss of power. We advocate that future studies should optimize the choice of the SWM using a small set of appropriate candidates. R functions to implement the optimization are available in the adespatial package and are detailed in a tutorial.

Human-elephant conflict (HEC) in Africa occurs wherever these two species coincide, and poses serious challenges to wildlife managers, local communities and elephants alike. Mitigation requires a detailed understanding of underlying patterns and processes. Although temporal patterns of HEC are relatively predictable, spatial variation has shown few universal trends, making it difficult to predict where conflict will take place. While this may be due to unpredictability in male elephant foraging behaviour (the male behaviour hypothesis) it may also be due to variations in the data resolution of earlier studies. 2. This study tested the male behaviour and data resolution hypotheses using HEC data from a 1000-km 2 unprotected elephant range adjacent to the Masai Mara National Reserve in Kenya. HEC incidents were divided into crop raiding and human deaths or injuries. Crop raiding was further subdivided into incidents involving only male elephants or family groups. A relatively fine-resolution, systematic, grid-based method was used to assign the locations of conflict incidents, and spatial relations with underlying variables were explored using correlation analysis and logistic regression. 3. Crop raiding was clustered into distinct conflict zones. Both occurrence and intensity could be predicted on the basis of the area under cultivation and, for male elephant groups, proximity to major settlements. Conversely, incidents of elephant-induced human injury and death were less predictable but were correlated with proximity to roads.

In the decade or so of renewed interest in neighborhood contexts and health, significant progress has been made conceptualizing the relationships between the urban environment and public health. Applied research on the link between the environment and health remains limited by the way spatial concepts, such as ''the neighborhood'' or ''the built environment'' are operationalized. In this paper we argue that representations of these spatial concepts in statistical models should be based upon the individuals, the place, and the problem under study. Through a series of simulation experiments we describe the sensitivity of estimates of the association between neighborhoods and health to the operationalization of spatial concepts. We explore the practice of conducting the same analysis at multiple scales and find that using model fit to ''discover'' the spatial dimension is problematic. In sum, there is a gap between our understanding of how the environment influences health and spatial statistical modeling techniques. For quantitative spatial inquiry into the relationship between the neighborhood environment and health to be effective this gap must be closed.

Extreme heat is an important weather hazard associated with excess mortality and morbidity. We determine the relative importance of heat exposure and the built environment, socioeconomic vulnerability, and neighborhood stability for heat mortality (Philadelphia, PA, USA) or heat distress (Phoenix, AZ, USA), using an ecologic study design. We use spatial Generalized Linear and Mixed Models to account for non-independence (spatial autocorrelation) between neighboring census block groups. Failing to account for spatial autocorrelation can provide misleading statistical results. Phoenix neighborhoods with more heat exposure, Black, Hispanic, linguistically and socially isolated residents, and vacant households made more heat distress calls. Philadelphia heat mortality neighborhoods were more likely to have low housing values and a higher proportion of Black residents. Our methodology can identify important risk factors and geographic areas to target interventions.

The possibility that homicides can spread from one geographic area to another has been entertained for some time by social scientists, yet systematic efforts to demonstrate the existence, or estimate the strength, of such a diffusion process are just beginning. This paper uses exploratory spatial data analysis (ESDA) to examine the distribution of homicides in 78 counties in, or around, the St. Louis metropolitan area for two time periods: a period of relatively stable homicide (1984)(1985)(1986)(1987)(1988)) and a period of generally increasing homicide (1988)(1989)(1990)(1991)(1992)(1993). The findings reveal that homicides are distributed nonrandomly, suggestive of positive spatial autocorrelation. Moreover, changes over time in the distribution of homicides suggest the possible diffusion of lethal violence out of one county containing a medium-sized city (Macon County) into two nearby counties (Morgan and Sangamon Counties) located to the west. Although traditional correlates of homicide do not account for its nonrandom spatial distribution across counties, we find some evidence that more affluent areas, or those more rural or agricultural areas, serve as barriers against the diffusion of homicides. The patterns of spatial distribution revealed through ESDA provide an empirical foundation for the specification of multivariate models which can provide formal tests for diffusion processes.

During the last decades immigration phenomenon reached a considerable importance, not only in research sector but also at public opinion level. Migration is a complex phenomenon demanding a system analysis which goes beyond demographic and economic considerations. The purpose of this study was to investigate the spatial structure of foreign presence in Italy in order to identify its geographical demarcation line among different interpretations. Traditional statistical analysis suggests different conventional indices allowing to quantify immigration phenomenon. Traditional indices, as Location Quotients and Segregation Index, have been compared to innovative indices including spatial statistics elements, as well as global and local indicators of spatial association. Such indicators have been created on the basis of available data for the case study, but also considering information which can be easily found in great part of national contexts.

Human-elephant conflict (HEC) in Africa occurs wherever these two species coincide, and poses serious challenges to wildlife managers, local communities and elephants alike. Mitigation requires a detailed understanding of underlying patterns and processes. Although temporal patterns of HEC are relatively predictable, spatial variation has shown few universal trends, making it difficult to predict where conflict will take place. While this may be due to unpredictability in male elephant foraging behaviour (the male behaviour hypothesis) it may also be due to variations in the data resolution of earlier studies. 2. This study tested the male behaviour and data resolution hypotheses using HEC data from a 1000-km 2 unprotected elephant range adjacent to the Masai Mara National Reserve in Kenya. HEC incidents were divided into crop raiding and human deaths or injuries. Crop raiding was further subdivided into incidents involving only male elephants or family groups. A relatively fine-resolution, systematic, grid-based method was used to assign the locations of conflict incidents, and spatial relations with underlying variables were explored using correlation analysis and logistic regression. 3. Crop raiding was clustered into distinct conflict zones. Both occurrence and intensity could be predicted on the basis of the area under cultivation and, for male elephant groups, proximity to major settlements. Conversely, incidents of elephant-induced human injury and death were less predictable but were correlated with proximity to roads.

We review various recent approaches to making digital soil maps based on geographic information systems (GIS) data layers, note some commonalities and propose a generic framework for the future. We discuss the various methods that have been, or could be, used for fitting quantitative relationships between soil properties or classes and their 'environment'. These include generalised linear models, classification and regression trees, neural networks, fuzzy systems and geostatistics. We also review the data layers that have been, or could be, used to describe the 'environment'. Terrain attributes derived from digital elevation models, and spectral reflectance bands from satellite imagery, have been the most commonly used, but there is a large potential for new data layers. The generic framework, which we call the scorpan-SSPFe (soil spatial prediction function with spatially autocorrelated errors) method, is particularly relevant for those places where soil resource information is limited. It is based on the seven predictive scorpan factors, a generalisation of Jenny's five factors, namely: (1) s: soil, other or previously measured attributes of the soil at a point; (2) c: climate, climatic properties of the environment at a point; (3) o: organisms, including land cover and natural vegetation; (4) r: topography, including terrain attributes and classes; (5) p: parent material, including lithology; (6) a: age, the time factor; (7) n: space, spatial or geographic position. Interactions (*) between these factors are also considered. The scorpan-SSPFe method essentially involves the following steps:

Extreme heat is an important weather hazard associated with excess mortality and morbidity. We determine the relative importance of heat exposure and the built environment, socioeconomic vulnerability, and neighborhood stability for heat mortality (Philadelphia, PA, USA) or heat distress (Phoenix, AZ, USA), using an ecologic study design. We use spatial Generalized Linear and Mixed Models to account for non-independence (spatial autocorrelation) between neighboring census block groups. Failing to account for spatial autocorrelation can provide misleading statistical results. Phoenix neighborhoods with more heat exposure, Black, Hispanic, linguistically and socially isolated residents, and vacant households made more heat distress calls. Philadelphia heat mortality neighborhoods were more likely to have low housing values and a higher proportion of Black residents. Our methodology can identify important risk factors and geographic areas to target interventions.

How can spatial location affect the operation of society, population or economic conditions? What is the role of neighbourhood and distance in social phenomena? In what way can a social organisation limit spatial barriers? How would spatial structures be affected by the attraction and repulsion of territorial units? Does society only use or also design regions? These questions are explored in this study.
This work analyses some important issues, concepts and analysis procedures of the territorial structure of society and social processes of spatiality. It does not contain a comprehensive theory of spatiality and regional science; it is primarily a practical empirical research.
Many theoretical works aim at defining the spatial structure of Europe. This article provides an overview of models describing the spatial structure of Europe. The study describes the economic spatial structure of Europe using bi-dimensional regression analysis, based on the gravity model. The spatial structure of Europe is illustrated with the help of the gravity model and spatial auto-correlation. With these patterns, it is possible to justify the appropriateness of the models based on different methodological backgrounds by comparing them with the results of this paper.
The subject of field theory concepts and methods that can aid regional analyses is examined, and attempts to offer a synthesised knowledge with a wide variety of examples and methods.

When sampling locations are known, the association between genetic and geographic distances can be tested by spatial autocorrelation or regression methods. These tests give some clues to the possible shape of the genetic landscape. Nevertheless, correlation analyses fail when attempting to identify where genetic barriers exist, namely, the areas where a given variable shows an abrupt rate of change. To this end, a computational geometry approach is more suitable because it provides the locations and the directions of barriers and because it can show where geographic patterns of two or more variables are similar. In this frame we have implemented Monmonier's (1973) maximum difference algorithm in a new software package to identify genetic barriers. To provide a more realistic representation of the barriers in a genetic landscape, we implemented in the software a significance test by means of bootstrap matrices analysis. As a result, the noise associated with genetic markers can be visualized on a geographic map and the areas where genetic barriers are more robust can be identified. Moreover, this multiple matrices approach can visualize the patterns of variation associated with different markers in the same overall picture. This improved Monmonier's method is highly reliable and can be applied to nongenetic data whenever sampling locations and a distance matrix between corresponding data are available.

Quantitative and qualitative methods are employed to investigate the extent to which proximity to 14 supportive housing facilities opening in Denver from 1992 to 1995 affects crime rates. The econometric specification provides pre-and post-controls for selection bias as well as a spatial autocorrelation correction. Focus groups with homeowners living near supportive housing provide richer context for interpreting the econometric results. The findings suggest that developers paying close attention to facility scale and siting can avoid negative neighborhood impacts and render their supportive housing invisible to neighbors. Implications for structuring local regulations and public education regarding supportive housing facilities follow.

A Spatio-Temporal Analysis of Dolphinfish; Coryphaena (August 2008) Hippurus, Abundance in the Western Atlantic: Implications for Stock Assessment of a Data-Limited Pelagic Resource. Abstract of a dissertation at the University of Miami. Dissertation supervised by Professor David Die. No. of pages in text. (331) Dolphinfish (Coryphaena hippurus) is a pelagic species that is ecologically and commercially important in the western Atlantic region. This species has been linked to dominant oceanographic features such as sea surface temperature (SST) frontal regions.

Many physical and social phenomena are embedded within networks of interdependencies, the so-called ‘context’ of these phenomena. In network analysis, this type of process is typically modeled as a network autocorrelation model. Parameter estimates and inferences based on autocorrelation
models, hinge upon the chosen specification of weight matrix W, the elements of which represent the influence pattern present in the network. In this paper I discuss how social influence processes can be incorporated in the specification of W. Theories of social influence center around 'communication’ and ‘comparison’; it is discussed how these can be operationalized in a network analysis context.
Starting from that, a series of operationalizations of W is discussed. Finally, statistical tests are presented that allow an analyst to test various specifications against one another or pick the best fitting model from a set of models.

Rapid urbanization has accelerated land use and land cover changes, and generated the urban heat island effect (UHI). Previous studies have reported positive effects of neighborhood landscapes on mitigating urban surface temperatures. However, the influence of neighborhood landscape spatial patterns on enhancing cooling effects has not yet been fully investigated. The main objective of this study was to assess the relationships between neighborhood landscape spatial patterns and land surface temperatures (LST) by using multi-regression models considering spatial autocorrelation issues. To measure the influence of neighborhood landscape spatial patterns on LST, this study analyzed neighborhood environments of 15,862 single-family houses in Austin, Texas, USA. Using aerial photos, geographic information systems (GIS), and remote sensing, FRAGSTATS was employed to calculate values of several landscape indices used to measure neighborhood landscape spatial patterns. After controlling for the spatial autocorrelation effect, results showed that larger and better-connected landscape spatial patterns were positively correlated with lower LST values in neighborhoods, while more fragmented and isolated neighborhood landscape patterns were negatively related to the reduction of LST.

There is an identifiable theoretical relationship between the comparable sales method (CSM) of valuation as practiced by mass appraisers and the recent developments in geostatistical valuation models. This paper provides an evaluation of techniques in respect of their treatment of location and their predictive capability. The CSM is shown to be a special case of a spatially lagged weight matrix

We investigate the common conjecture in applied econometric work that the inclusion of spatial fixed effects in a regression specification re- moves spatial dependence. We demonstrate analytically and by means of a series of simulation experiments how evidence of the removal of spatial autocorrelation by spatial fixed effects may be spurious when the true DGP takes the form of a

A mosaic of habitation at Zeewijk
The third and final excavation analysed in
further detail as part of the Odyssey ‘Unlocking
Noord-Holland's Late Neolithic Treasure Chest’
project was that performed at the Zeewijk site
in 1992, 1993 and 1994. Zeewijk, named after a
farm established by the first colonists of the
Groetpolder, was regarded as a very promising
site, but also a challenging one, considering the
huge backlog. The large size and very high
quantity of finds, the fact that the area was
only partially excavated and the potential for
sample selection within the project meant that
the narrative capacity of Zeewijk was of a
different order.
At Zeewijk, two large areas of cultural layer
were distinguished in the 1980s, referred to as
Zeewijk-West and Zeewijk-West. Both proved to
be located on the sandy levees along a filled
creek gully. About 15-20% was excavated,
distributed among East and West and over three
campaigns. In 1992, a large feature with a
wooden post was found at Zeewijk-East and in
1993 it became clear that it belonged to
remarkable large structure measuring 22 by 7 m.
At Zeewijk-West, the number of features is very
high, especially on the highest parts of the levee.
In this area five possible house plans were
recognised. These buildings vary from approx. 6
to 14 m in length and are approx. 3.5 to 4.5 m
wide. Based on the preliminary results from the
analyses of the 1992 campaign and
interpretation of the large structure, the Zeewijk
site was interpreted at the time as a large, more
permanent residential settlement.
All kinds of specialists worked closely
together to reveal all the cultural/ecological
details and other research data, and to
thoroughly integrate all the information,
focusing on the same research questions as
those addressed in the analysis of Keinsmerbrug
and Mienakker. The project team consisted of 16
people working at different organisations
(commercial agencies, universities and the
Cultural Heritage Agency), each of whom
contributed their own particular expertise.
Due to the sampling strategy during the
excavation campaigns, the selection during our
project and some missing find categories, the
spatial analysis of the find distributions and
posthole clusters was very limited. No clear
structures were identified. The numerous
postholes, cow hoofprints and ard marks
(occurring over a large area measuring about 1
ha) suggest a large settlement area with
farmland. All human activities seemed to be
arranged in a mosaic pattern: habitation,
ploughing, growing crops on small arable fields
and raising cattle all occurred simultaneously,
successively (all year round) and shifting
spatially. Differences in the ceramic assemblage
point to different episodes of occupation. Based
on typochronological arguments, Zeewijk-East
and the northern part of Zeewijk-West can be
seen as the earliest phase, perhaps
contemporaneous, while the southern part of
Zeewijk-West is the latest. In this sequence, the
construction of the large structure of Zeewijk-
East, cutting through the numerous ard marks
and the tearing down of this building and reuse
of the wood from the wall posts could have been
the final act on the eastern side of the gully.
Habitation in the southern part of Zeewijk-West
continued, while Zeewijk-East was used for
activities other than habitation, or may have
been abandoned. The central posts of the large
structure remained visible for some time after.
The settlers of Zeewijk chose as their
settlement site two sandy ridges separated by
an active gully in a varied, fairly open
environment. The levees were covered with
plants, shrubs and trees such as willow, alder,
ash, bird cherry and field maple. The low-lying
parts of these saline and brackish wetlands are
more open, with a great diversity of grasses and
herbaceous plants, making ideal pasture for
cattle. Although this landscape is dominated by
marine influences, there are also places at or
near the settlement were fresh water
accumulates and where beavers lived.
The people of Zeewijk were experienced in
different fishing techniques that enabled them
to exploit the abundant waters of the tidal
creeks. They were able to catch large and small
fish, probably with traps, weirs or fences. The
large numbers of ducks and geese were probably
caught in the moulting period. Beaver were also
hunted, as well as other fur animals like stoat,
brown bear and wildcat, although these hides could have been passed on as exchanged goods.
The hunting of wild boar played a minor but not insignificant role. Cattle were by far the most important food source in terms of meat supply.
The abundance of cow hoofprints shows the importance of keeping cattle close by. Though sheep/goats, pigs and dog did forage around the settlement, they were not eaten as frequently. The inhabitants also occasionally harvested food at low tide from the extensive mussel banks in tidal gullies and on sandbanks.
Naked barley and emmer wheat were both grown, as was flax, for its oil-bearing seeds and for its fibres. The farmers brought complete ears of barley and wheat to the settlement, possibly with the stalks still attached. Cultivation was probably small-scale and intensive. The small fields were located on the levees, close to the houses. Cereals were ground, pounded and processed into two types of porridge-like food, one made of coarsely crushed cereals, while the other was a compact, mushy food of finely ground grain. The consumption of acorns was also an important food source. Thin-walled beakers were used to cook the cereals and/or acorns into thick porridge or soup. Charred residue on a ceramic plate fragment indicates that it was used as a griddle. Zeewijk is the first Dutch prehistoric site where use of ceramic plates for baking has been demonstrated.
Stone, flint and amber were collected on the nearby beach or on the higher boulder clay outcrop at Wieringen, where the raw material lay on the surface. Jet could also be found on the nearby beach, but it may also have been obtained by exchange. The southern flint was evidently obtained via long-distance networks. The inhabitants used the flint to make all kinds of tools, including borers and scrapers, which they used for working wood, cleaning skins, scraping fish scales, cutting fish skins/cattle hides and making amber beads. Evidence of craftsmanship is more apparent than at Mienakker. The production of amber ornaments, and maybe of bone beads and ‘ripples’, spinning and weaving were all activities performed at the site.
Zeewijk is regarded as a large domestic settlement, occupied all year round. We would characterise Zeewijk as a mosaic-like palimpsest, reflecting recurrent habitation alternating with agrarian activities. The local crafts, the large variety in ceramics and the construction and use of the large ceremonial building in East suggests that different groups of Corded Ware households lived at Zeewijk. In our view, this was a community of several families related by kinship both genetic and affinal. How many domestic social units lived there simultaneously or in successive generations is unclear, but the settlers of Zeewijk indisputably knew how to live in this environment.

The quality of maps obtained by interpolation of observations of a target environmental variable at a restricted number of locations, is partly determined by the spatial pattern of the sample locations. A method is presented for optimization of the sample pattern when the environmental variable is interpolated with the help of exhaustively known covariates, which are assumed to be linearly related to the target variable. In this method the spatially averaged universal kriging variance (MUKV), which incorporates trend estimation error as well as spatial interpolation error, is minimized. The optimal pattern is obtained using simulated annealing. The method requires that the covariance function or variogram of the regression-residuals is known. The method is tested in a case study on the Mean Highest Water table in a coversand area in The Netherlands. The patterns of 25, 50 and 100 sample locations are optimized and compared with the patterns optimized with the ordinary kriging (OK) model (assuming no trend) and with the multiple linear regression (MLR) model (assuming no spatial autocorrelation of residuals). The results show that the UK-patterns are a good compromise between spreading in geographic space and feature space. The MUKV for the UK-patterns is 19% (n = 25), 7% (n = 50) and 3% (n = 100) smaller than for the OK-patterns. Compared with the MLR-patterns the reduction is 2%, 4% and 4%, respectively.

Ordinary kriging and cokriging are two geostatistical techniques used to create continuous maps of spatially autocorrelated attributes. Both procedures use the same primary variable, but cokriging, like multivariate statistics, incorporates additional independent variables. In this study, the primary variable is cubic foot volume and the secondary variable, mean normalized difference vegetation index, is calculated from an August 1996 Landsat Thematic

The aim of this study was to quantify the environmental and genetic effects on early growth of Nile tilapia, Oreochromis niloticus, in hapa-in-earthen pond systems. In a pilot study, we grew swim-up fry with or without supplementary feed in hapas suspended in fertilized ponds at 5, 10, 15, and 20 fry/m 2 densities. In the main experiment, we reared swim-up fry from 25 fullsib families separately for 42 days at 15 fry/m 2 density in hapas suspended in two earthen ponds. Hapas were arranged in two column arrays along the sides of the ponds. Ponds were fertilized daily with chicken manure. In addition, fry in one column in each pond were fed twice daily on 40% protein pelleted feed. Results from the pilot study indicated significant effects of stocking density and treatment. In the main experiment, the dietary treatment effect was not significant but there were large differences in growth between ponds. Mean body weight at 42 days was 1.7 g in pond A and 0.4 g in pond B. Fry heritability (h 2 ) of 42-day fry body weight estimated from the whole data set using a univariate model was 0.01 ± 0.06. The bivariate heritability estimates were 0.59 ± 0.19 in pond A and 0.05 ± 0.11 in pond B. The common environmental/hapa (c 2 ) effects were 0.14 ± 0.06 and 0.29 ± 0.07 in respective ponds. We found significant positive spatial autocorrelation (P = 0.02) indicating resemblance in growth of fry in neighboring hapas. Analysis of environmental variables showed that the two ponds differed significantly in dissolved oxygen. The low genetic correlation (r g = − 0.27 ± 0.69) between body weights of fry in both ponds therefore might suggest genotype by environment interactions for tolerance to low dissolved oxygen in Nile tilapia juveniles.

The paper evaluates spreading of observations in feature and geographical spaces as a key to sampling optimisation for spatial prediction by correlation with auxiliary maps. Although auxiliary data are commonly used for mapping soil variables, problems associated with the design of sampling strategies are rarely examined. When generalised least-squares estimation is used, the overall prediction error depends upon spreading of points in both feature and geographical space. Allocation of points uniformly over the feature space range proportionally to the distribution of predictor (equal range stratification, or ER design) is suggested as a prudent sampling strategy when the regression model between the soil and auxiliary variables is unknown. An existing 100-observation sample from a 50 by 50 km soil survey in central Croatia was used to illustrate these concepts. It was re-sampled to 25-point datasets using different experimental designs: ER and 2 response surface designs. The designs were compared for their performance in predicting soil organic matter from elevation (univariate example) using the overall prediction error as an evaluation criterion. The ER design gave overall prediction error similar to the minmax design, suggesting that it is a good compromise between accurate model estimation and minimisation of spatial autocorrelation of residuals. In addition, the ER design was extended to the multivariate case. Four predictors (elevation, temperature, wetness index, and NDVI) were transformed to standardised principal components. The sampling points were then assigned to the components in proportion to the variance explained by a principal component analysis and following the ER design. Since stratification of the feature space results in a large number of possible points in each cluster, the spreading in geographical space can also be maximised by selecting the best of several realisations. S R 0 3 0 0 5 T . He n g l e t a l .S a mp l i n g s t r a t e g i e s f o r s p a t i a l p r e d i c t i o n b y c o r r e l a t i o n Additional keywords: response surface design, soil survey, general least squares, feature space, principal components. Aust. J. Soil Res. T. Hengl et al.

Quality of some processes or products can be characterized effectively by a function referred to as profile. Many studies have been done by researchers on the monitoring of simple linear profiles when the observations within each profile are uncorrelated. However, due to spatial autocorrelation or time collapse, this assumption is violated and leads to poor performance of the proposed control charts. In this paper, we consider a simple linear profile and assume that there is a first order autoregressive model between observations in each profile. Here, we specifically focus on phase II monitoring of simple linear regression. The effect of autocorrelation within the profiles is investigated on the estimate of regression parameters as well as the performance of control charts when the autocorrelation is overlooked. In addition, as a remedial measure, transformation of Y-values is used to eliminate the effect of autocorrelation. Four methods are discussed to monitor simple linear profiles and their performances are evaluated using average run length criterion. Finally, a case study in agriculture field is investigated.

This paper presents spatially explicit analyses of the greenspace contribution to residential property values in a hedonic model. The paper utilizes data from the housing market near downtown Los Angeles. We first used a standard hedonic model to estimate greenspace effects. Because the residuals were spatially autocorrelated, we implemented a spatial lag model as indicated by specification tests. Our results show that neighborhood greenspace at the immediate vicinity of houses has a significant impact on house prices even after controlling for spatial autocorrelation. The different estimation results from non-spatial and spatial models provide useful bounds for the greenspace effect. Greening of inner city areas may provide a valuable policy instrument for elevating depressed housing markets in those areas.

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.

The purpose of this paper is to implement an efficient method for GIS‐based traffic analysis zone (TAZ) design in order to evaluate and validate such a method. The method was developed by the authors.Moran's I spatial autocorrelation coefficient and sample variance are used for evaluating the generated TAZs using the Champaign‐Urbana, IL region as a case study. Sensitivity analysis is

Contemporary resource management practice and rural development planning increasingly emphasize the integration of resource extractive industries with non-market-based recreational and amenity values. There is a growing empirical literature which suggests that natural amenities impact regional economies through aggregate measures of economic performance such as population, income, and/or employment growth, and housing development. We maintain that assessing the developmental aspects of amenity-led regional change requires a more thorough focus on alternative measures of economic performance such as income distribution and spatial organization. In the applied research presented here we investigate relationships between amenities and regional economic development indicators. Results suggest mixed and generally insignificant amenity-based associations which highlight the need for appropriate regional economic modeling techniques that account for often dramatic spatial autocorrelation of natural amenity attributes. We conclude that with respect to amenity driven economic growth and development "place in space" matters.