Showing papers on "Spatial analysis published in 1993"
6,278 citations
TL;DR: Cressie et al. as discussed by the authors presented the Statistics for Spatial Data (SDS) for the first time in 1991, and used it for the purpose of statistical analysis of spatial data.
Abstract: 5. Statistics for Spatial Data. By N. Cressie. ISBN 0 471 84336 9. Wiley, Chichester, 1991. 900 pp. £71.00.
5,555 citations
TL;DR: The paper discusses first how autocorrelation in ecological variables can be described and measured, and ways are presented of explicitly introducing spatial structures into ecological models, and two approaches are proposed.
Abstract: ilbstract. Autocorrelation is a very general statistical property of ecological variables observed across geographic space; its most common forms are patches and gradients. Spatial autocorrelation. which comes either from the physical forcing of environmental variables or from community processes, presents a problem for statistical testing because autocorrelated data violate the assumption of independence of most standard statistical procedures. The paper discusses first how autocorrelation in ecological variables can be described and measured. with emphasis on mapping techniques. Then. proper statistical testing in the presence of autocorrelation is briefly discussed. Finally. ways are presented of explicitly introducing spatial structures into ecological models. Two approaches are proposed: in the raw-data approach, the spatial structure takes the form of a polynomial of the x and .v geographic coordinates of the sampling stations; in the matrix approach. the spatial structure is introduced in the form of a geographic distance matrix among locations. These two approaches are compared in the concluding section. A table provides a list of computer programs available for spatial analysis.
3,491 citations
TL;DR: Methods of basis change for socioeconomic data are reviewed and are seen to differ in the assumptions made in each about underlying density surfaces, and an illustration is provided by using Californian data.
Abstract: Spatial data are collected and represented as attributes of spatial objects embedded in a plane. Basis change is defined as the transfer of attributes from one set of objects to another. Methods of basis change for socioeconomic data are reviewed and are seen to differ in the assumptions made in each about underlying density surfaces. These methods are extended to more general cases, and an illustration is provided by using Californian data. The implementation of this framework within a geographical information system is discussed.
379 citations
TL;DR: This paper has made some powerful enhancements to the S-Plus system to produce a tool for display and analysis of spatial point pattern data.
337 citations
TL;DR: This paper presents a statistical approach, originally developed for mapping disease risk, to ecological regression analysis in the presence of spatial autocorrelated extra-Poisson variation.
Abstract: This paper presents a statistical approach, originally developed for mapping disease risk, to ecological regression analysis in the presence of spatial autocorrelated extra-Poisson variation. An insight into the effect of allowing for spatial autocorrelation on the relationship between disease rates and explanatory variables is given. Examples based on cancer frequency in Scotland and Sardinia are used to illustrate the interpretation of regression coefficient and further methodological issues.
286 citations
01 Aug 1993
TL;DR: This paper motivates four different user defined window query classes and derives a probabilistic model for each of them in terms of the expected number of data bucket accesses needed to perform a window query.
Abstract: In this paper, we motivate four different user defined window query classes and derive a probabilistic model for each of them. For each model, we characterize the efficiency of spatial data structures in terms of the expected number of data bucket accesses needed to perform a window query. Our analytical approach exhibits the performance phenomena independent of data structure and implementation details and whether the objects are points or non-point objects.
251 citations
23 Jun 1993
TL;DR: A spatial logic which can be used to reason about topological and spatial relationships among objects in spatial databases is presented and how the formalism can be extended to include orientation and metrical information is shown.
Abstract: In this paper, we present a spatial logic which can be used to reason about topological and spatial relationships among objects in spatial databases. The main advantages of such a formalism are its rigorousness, clear semantics and sound inference mechanism. We also show how the formalism can be extended to include orientation and metrical information. Comparisons with other formalisms are discussed.
161 citations
01 Jan 1993
TL;DR: The study shows that knowledge discovery has wide applications in spatial databases, and relatively efficient algorithms can be developed for discovery of general knowledge in large spatial databases.
Abstract: Extraction of interesting and general knowledge from large spatial databases is an important task in the development of spatial dataand knowledge-base systems. In this paper, we investigate knowledge discovery in spatial databases and develop a generalization-based knowledge discovery mechanism which integrates attribute-oriented induction on nonspatial data and spatial merge and generalization on spatial data. The study shows that knowledge discovery has wide applications in spatial databases, and relatively efficient algorithms can be developed for discovery of general knowledge in large spatial databases.
148 citations
19 Apr 1993
TL;DR: A class of tree structures, called generalization trees, that can be applied efficiently to compute spatial joins in a hierarchical manner are described.
Abstract: Spatial joins are join operations that involve spatial data types and operators. Due to basic properties of spatial data, many conventional join strategies suffer serious performance penalties or are not applicable at all. The join strategies known from conventional databases that can be applied to spatial joins and the ways in which some of these techniques can be modified to be more efficient in the context of spatial data are discussed. A class of tree structures, called generalization trees, that can be applied efficiently to compute spatial joins in a hierarchical manner are described. The performances of the most promising strategies are analytically modeled and compared. >
TL;DR: In this article, a novel feature of the data is replication and nesting in a sampling design: multiple spatial patterns were observed from each of several animals, and a ratio regression approach was developed.
Abstract: SUMMARY Techniques for analysing three-dimensional spatial point patterns are demonstrated on data from a confocal microscope recording the locations of cells in three dimensions. New computational techniques are proposed for edge corrections and empty space measurement. A novel feature of the data is replication and nesting in a sampling design: multiple spatial patterns were observed from each of several animals. For this we develop a ratio regression approach.
TL;DR: In this article, a spatial unilateral autoregressive moving average (ARMA) model of first order is defined and its properties studied for two-dimensional spatial data, and a simple condition for stationarity and conditional expectation (interpolation) properties of the model is given.
Abstract: For two-dimensional spatial data, a spatial unilateral autoregressive moving average (ARMA) model of first order is defined and its properties studied. The spatial correlation properties for these models are explicitly obtained, as well as simple conditions for stationarity and conditional expectation (interpolation) properties of the model. The multiplicative or linear-by-linear first-order spatial models are seen to be a special case which have proved to be of practical use in modeling of two-dimensional spatial lattice data, and hence the more general models should prove to be useful in applications. These unilateral models possess a convenient computational form for the exact likelihood function, which gives proper treatment to the border cell values in the lattice that have a substantial effect in estimation of parameters. Some simulation results to examine properties of the maximum likelihood estimator and a numerical example to illustrate the methods are briefly presented.
23 Jun 1993
TL;DR: The 9-intersection is applied, a frequently used formalism for topological spatial relations between objects represented in a vector data model, and it is found that the set of all possible topological relations between regions in ρ2 is a subset of the topological Relations that can be realized between two bounded, extended objects in ℤ2.
Abstract: Users of geographic databases that integrate spatial data represented in vector and raster models, should not perceive the differences among the data models in which data are represented, nor should they be forced to apply different concepts depending on the model in which spatial data are represented. A crucial aspect of spatial query languages for such integrated systems is the need mechanisms to process queries about spatial relations in a consistent fashion. This paper compares topological relations between spatial objects represented in a continuous (vector) space of ρ2 and a discrete (raster) space of ℤ2. It applies the 9-intersection, a frequently used formalism for topological spatial relations between objects represented in a vector data model, to describe topological relations for bounded objects represented in a raster data model. We found that the set of all possible topological relations between regions in ρ2 is a subset of the topological relations that can be realized between two bounded, extended objects in ℤ2. At a theoretical level, the results contribute toward a better understanding of the differences in the topology of continuous and discrete space. The particular lesson learnt here is that topology in ρ2 is based on coincidence, whereas in ℤ2 it is based on coincidence and neighborhood. The relevant differences between the raster and the vector model are that an object's boundary in ℤ2 has an extent, while it has none in ρ2; and in the finite space of ℤ2 there are points between which one cannot insert another one, while in the infinite space of ρ2 between any two points there exists another one.
TL;DR: In this paper, scale of fluctuation analysis is used to estimate the dimensional extent to which data are significantly autocorrelated by observing the behavior of sample variance under extended local averaging.
TL;DR: In this article, the authors compare the design-based and model-based approaches for local estimation of the areal fractions saturated with phosphate and show that the former has the desirable property of unbiasedness and the latter does not.
Abstract: The perspectives and concepts of the classical sampling or design-based approach and the geostatistical or model-based approach are compared. We show that unbiasedness and minimum variance in the design-based approach is quite different from that in the model-based approach and that design-based strategies are always valid, whether or not there is spatial autocorrelation. Model-based predictions of spatial means will generally not have the desirable property of unbiasedness in the design-based sense. Model-based strategies contain a risk arising from biased selection and they do not allow the accuracy of predictions to be assessed objectively, i.e., based on the sample data alone. Model-based strategies are useful for local estimation, i.e., for many small blocks and points, provided that there are enough data to estimate the variogram. In a case study on phosphate saturation, design-based and model-based estimates of the areal fractions saturated with phosphate were similar, but with smaller blocks the differences increased to magnitudes of practical importance.
TL;DR: This book, which contains contributions from a wide-ranging group of international scholars, demonstrates the progress which has been achieved so far at the interface of GIS technology and spatial analysis and planning.
Abstract: Geographical Information Systems (GIS) provide an enhanced environment for spatial data processing. The ability of geographic information systems to handle and analyze spatially referenced data may be seen as a major characteristic which distinguishes GIS from information systems developed to serve the needs of business data processing as well as from CAD systems or other systems whose primary objective is map production. This book, which contains contributions from a wide-ranging group of international scholars, demonstrates the progress which has been achieved so far at the interface of GIS technology and spatial analysis and planning. The various contributions bring together theoretical and conceptual, technical and applied issues. Topics covered include the design and use of GIS and spatial models, AI tools for spatial modelling in GIS, spatial statistical analysis and GIS, GIS and dynamic modelling, GIS in urban planning and policy making, information systems for policy evaluation, and spatial decision support systems.
Book•
01 Mar 1993
TL;DR: This work assesses Variability, Shape, and Pattern of Map Features, and overlaying Maps and Characterizing Error Propagation, as well as measuring Effective Distance and Connectivity.
Abstract: Maps as Data and Data Structure Implications. Measuring Effective Distance and Connectivity. Roving Windows: Assessment of Neighborhood Characteristics. What GIS Is and Isn't: Spatial Data Mapping, Management, Modeling, and More. Assessing Variability, Shape, and Pattern of Map Features. Overlaying Maps and Characterizing Error Propagation. Overlaying Maps and Summarizing the Results. Scoping GIS: What to Consider. Slope, Distance, and Connectivity: Their Algorithms. Cartographic and Spatial Modeling. Epilog. Appendices. Glossary. Index.
01 Jan 1993
19 Sep 1993
TL;DR: A different perspective on spatial information theories is offered, taking the point of view of people trying to solve spatial problems by using a GIS, and it is concluded that a cognitive linguistics perspective on metaphors best matches the requirements for user level theories.
Abstract: The notion of a spatial information theory is often understood in the sense of a theory underlying the design and implementation of geographic information systems (GIS). This paper offers a different perspective on spatial information theories, taking the point of view of people trying to solve spatial problems by using a GIS. It discerns a need for user level theories about spatial information and describes requirements for them. These requirements are then compared with various views on metaphors held in computer science and cognitive linguistics. It is concluded that a cognitive linguistics perspective on metaphors best matches the requirements for user level theories. Therefore, the user's needs for theories of spatial information should be dealt with by explicitly crafting metaphors to handle spatial information by human beings. The paper discusses traditional and possible future metaphor sources for spatial information handling tasks.
TL;DR: This paper examines important interactions between processes and spatial structure in systems of subpopulations with migration and drift, by analyzing correlations of gene frequencies over space and time, using space-time autoregressive (STAR) stochastic spatial time series to develop novel estimators for migration rates.
Abstract: The geographic distribution of genetic variation is an important theoretical and experimental component of population genetics. Previous characterizations of genetic structure of populations have used measures of spatial variance and spatial correlations. Yet a full understanding of the causes and consequences of spatial structure requires complete characterization of the underlying space-time system. This paper examines important interactions between processes and spatial structure in systems of subpopulations with migration and drift, by analyzing correlations of gene frequencies over space and time. We develop methods for studying important features of the complete set of space-time correlations of gene frequencies for the first time in population genetics. These methods also provide a new alternative for studying the purely spatial correlations and the variance, for models with general spatial dimensionalities and migration patterns. These results are obtained by employing theorems, previously unused in population genetics, for space-time autoregressive (STAR) stochastic spatial time series. We include results on systems with subpopulation interactions that have time delay lags (temporal orders) greater than one. We use the space-time correlation structure to develop novel estimators for migration rates that are based on space-time data (samples collected over space and time) rather than on purely spatial data, for real systems. We examine the space-time and spatial correlations for some specific stepping stone migration models. One focus is on the effects of anisotropic migration rates. Partial space-time correlation coefficients can be used for identifying migration patterns. Using STAR models, the spatial, space-time, and partial space-time correlations together provide a framework with an unprecedented level of detail for characterizing, predicting and contrasting space-time theoretical distributions of gene frequencies, and for identifying features such as the pattern of migration and estimating migration rates in experimental studies of genetic variation over space and time.
TL;DR: The empirical performance of three indices of spatial autocorrelation (Moran's I, Geary's c and a rank adjacency statistic D) in the analysis of regional cancer incidence data is described and the power of these indices to detect likely disease patterns is estimated by stimulation.
Abstract: We describe the empirical performance of three indices of spatial autocorrelation (Moran's I, Geary's c and a rank adjacency statistic D) in the analysis of regional cancer incidence data. Heterogeneity in regional population sizes and age structure leads to variable precision in estimated rates; the usual methods for assessing I, c and D, which ignore such heterogeneity, are shown to be liberally biased, especially for c and D. The power of these indices to detect likely disease patterns is estimated by stimulation; the power is quite variable, depending on the exact pattern assumed, although I tends to have the highest power. The null distributions appear quite robust in small samples, even when several regions have no observed case. Preliminary work on the Ontario cancer registry showed generally unimportant effects on the spatial analysis of variation in case registration rates or missing residence data.
TL;DR: In this article, a general statistical framework is proposed for comparing linear models of spatial process and pattern, based on either fixed effects or random effects, for nested analysis of variance can be found.
Abstract: A general statistical framework is proposed for comparing linear models of spatial process and pattern. A spatial linear model for nested analysis of variance can be based on either fixed effects or random effects. Greig-Smith (1952) originally used a fixed effects model, but there are also examples of random effects models in the soil science literature. Assuming intrinsic stationarity for a linear model, the expectations of a spatial nested ANOVA and two term local variance (TTLV, Hill 1973) are functions of the variogram, and several examples are given. Paired quadrat variance (PQV, Ludwig & Goodall 1978) is a variogram estimator which can be used to approximate TTLV, and we provide an example from ecological data. Both nested ANOVA and TTLV can be seen as weighted lag-1 variogram estimators that are functions of support, rather than distance. We show that there are two unbiased estimators for the variogram under aggregation, and computer simulation shows that the estimator with smaller variance depends on the process autocorrelation.
TL;DR: In this paper, the influence of spatial autocorrelation in original measurements and regression residuals is examined using semi-variogram analysis at several spatial resolutions, and a sampling scheme is proposed to examine the effects of auto-correlation on predictive linear models in cases of small sample sizes.
Abstract: This article describes research related to sampling techniques for establishing linear relations between land surface parameters and remotely-sensed data. Predictive relations are estimated between percentage tree cover in a savanna environment and a normalized difference vegetation index (NDVI) derived from the Thematic Mapper sensor. Spatial autocorrelation in original measurements and regression residuals is examined using semi-variogram analysis at several spatial resolutions. Sampling schemes are then tested to examine the effects of autocorrelation on predictive linear models in cases of small sample sizes. Regression models between image and ground data are affected by the spatial resolution of analysis. Reducing the influence of spatial autocorrelation by enforcing minimum distances between samples may also improve empirical models which relate ground parameters to satellite data.
01 Jan 1993
TL;DR: In this article, a general statistical framework is proposed for comparing linear models of spatial process and pattern, and two unbiased estimators for the variogram under aggregation are presented, and computer simulation shows that the estimator with smaller variance depends on Ihe process autocorrelation.
Abstract: AbstracL A general statistical framework is proposed for comparing linear models of spatial process and pattern. A spatial linear model for nested analysis of variance can be based on either fixed effects or random effects. Greig-Smith (1952) originally used a fixed effects model, but there are also examples of random effects models in Lhe soil science literature. Assuming imrinsic stationarity for a linear model, the expectations of a spatial nested ANOVA lllld (wo teon local variance (lTLV, Hill 1973) are funclions of the variogram, and several examples are given. Paired quadrat variance (PQV. Ludwig & Goodall 1978) is a variogram estimator which can be used 10 approximate TIl..V. and we provide an example from ecological data. BOIh nested ANOVA and TILV can be seen as weighted lag-I variogram estimators that are functions of support, rather than distance. We show that there are two unbiased estimators for the variogram under aggregation, and computer simulation shows that the estimator with smaller variance depends on Ihe process autocorrelation.
01 Jan 1993
TL;DR: This document develops and outlines a strategy in which field variables are used to enable modelers to work directly with the spatial data as spatially continuous phenomena, and considers the potential for the definition of vector fields and related operations using this strategy.
Abstract: Linking a GIS to a spatially distributed, physically-based environmental model offers many advantages. However, the implementation of such linkages is generally problematic. Many problems arise because the relationship between the reality being represented by the mathematical model and the data model used to organize the spatial data in the GIS has not been rigorously defined. In particular, while many environmental models are based on theories that assume continuity and incorporate physical fields as independent variables, current GISs can only represent continuous phenomena in a variety of discrete data models. This document develops and outlines a strategy in which field variables are used to enable modelers to work directly with the spatial data as spatially continuous phenomena. Several outcomes from the use of this strategy are explored. Modelers can express their spatial data needs as representations of reality, rather than as elements of a GIS database, and a GIS-independent language for model development results. By providing a formal linkage between the various models of spatial phenomena, a mechanism is created for the explicit expression of transformation rules between the models of spatial data stored and manipulated by GIS. The incorporation of field variables allows several operations (such as determining integrals, slope and aspect) and reserved variables (such as latitude and longitude) which are commonly used in environmental models to be defined. While scalar fields are the focus of this document, consideration of the potential for the definition of vector fields and related operations (such as divergence and gradient) using this strategy is also included.
01 Oct 1993-Cartographica: The International Journal for Geographic Information and Geovisualization
TL;DR: In this article, the authors develop design requirements for visualization of spatial data quality based on characterizations of quality, a range of quality assessment tasks, and different contexts under which data quality might be investigated.
Abstract: Visualization encompasses the display of quantities or qualities of visible or invisible phenomena through the combined use of points, lines, a coordinate system, numbers, symbols, words, shading, color, and animation. The objectives of visualization are to provoke insights and expand comprehension of information by revealing complex relationships among data. Geographical information is visualized in the form of maps. Recent concern over the accuracy and reliability of spatial information in geographic information systems has raised an interest in applying visualization tools to comprehend and communicate the reliability of GIS information and products. This paper develops design requirements for visualization of spatial data quality based on characterizations of quality, a range of quality assessment tasks, and different contexts under which data quality might be investigated. La visualisation comprend l'affichage de phenomenes quantitatifs ou qualitatifs, visibles ou invisibles, au moyen de l'usage comb...