- Atlas
- Mathematics
- Spatial Statistics
Spatial Statistics
Spatial statistics is the branch of statistics that deals with data whose values are tied to locations and whose nearby values tend to resemble one another.
7 frameworks, from 1950 to today · Statistics · Mathematics
Overview
Spatial statistics is the branch of statistics that deals with data whose values are tied to locations and whose nearby values tend to resemble one another12. That single fact—that geography breaks the usual assumption that observations are independent—is what makes the field necessary2. If you sample air pollution at monitoring stations, house prices across a city, or disease cases across a country, a station's reading tells you something about its neighbours' readings32. Standard statistics treats that as a nuisance or a violation; spatial statistics treats it as the central object of study2. Its history is a sequence of attempts to describe that dependence, to use it for prediction, and to test whether apparent patterns could have arisen by chance.
Early mapping and the roots of spatial thinking
Long before formal theory, practical people noticed spatial dependence. John Snow's 1854 map of cholera deaths around the Broad Street pump in London is the canonical early example of using the location of cases to reason about a cause, though Snow's argument was primarily about water supply rather than a statistical model of spatial association. In the nineteenth and early twentieth centuries, cartographers and geologists developed interpolation by hand: drawing contours through scattered measurements, a practice that already assumed nearby points are more alike than distant ones.
The first formal statistical treatment of spatial dependence came from agronomy. In the 1920s and 1930s, R. A. Fisher and colleagues at Rothamsted Experimental Station developed the analysis of field trials, where plots laid out in a grid are subject to soil variation that is itself spatially structured. Fisher's randomization and blocking designs were, in part, a way to neutralize spatial dependence so that treatment effects could be estimated cleanly. The complementary question—how to model that dependence—came later.
Geostatistics: from mining to kriging
The decisive turn came from mining. In the 1950s, Danie Krige, a South African mining engineer, noticed that when estimating the grade of gold ore from borehole samples, the standard formulas gave unreliable answers because samples close together carried redundant information. He developed empirical weighting schemes that down-weighted clustered samples. In the 1960s, the French mathematician Georges Matheron formalized Krige's intuition into what he named the theory of regionalized variables, and the method of optimal spatial prediction became known as kriging in Krige's honour.
The core idea is the variogram: a function describing how the dissimilarity between two measurements grows with the distance separating them4. From an estimated variogram, one can compute the best linear unbiased prediction at an unobserved location—a weighted average of nearby observations, with weights chosen to minimize prediction variance. This made it possible to produce not just a map but a map with error bars. Geostatistics spread from mining into hydrology, soil science, and environmental monitoring, and by the 1980s it was a standard tool in the earth sciences. The 1990s saw it absorbed into mainstream statistics through the work of Noel Cressie, whose 1991 book Statistics for Spatial Data reframed kriging as a special case of linear mixed models, connecting it to the general theory of best linear unbiased prediction.
Point patterns: asking whether events cluster
A second strand concerned events that occur at points—trees in a forest, disease cases in a city, crimes on a street network. The question is whether the points are more clustered, more regular, or more random than chance would produce. The foundational tool was the nearest-neighbour distance distribution, and in the 1950s and 1960s ecologists and statisticians developed tests based on it. The key advance was the Ripley's K-function, introduced by Brian Ripley in 1976, which summarizes clustering across all distance scales rather than at a single nearest-neighbour distance. A related line, the analysis of quadrat counts (counting events in grid cells and testing against Poisson variation), had been used since the 1920s but was limited by the arbitrary choice of cell size.
Point pattern analysis became a mature field through the 1980s and 1990s, with the development of edge corrections (because points near a study boundary have fewer neighbours than interior points), inhomogeneous models (where the underlying intensity varies across space), and space-time extensions. The 2000s brought spatstat, an open-source R package by Adrian Baddeley and Rolf Turner, which made the full toolkit accessible and is now the standard reference implementation.
Areal and lattice models: when space is a set of regions
A third tradition dealt with data aggregated to regions—census tracts, counties, countries—where each unit has a value and neighbours are defined by adjacency. The central problem is that neighbouring regions tend to have similar values, and ignoring this inflates apparent significance. The Moran's I statistic, introduced by Patrick Moran in 1950, measures global spatial autocorrelation: whether values are more similar among neighbours than expected under randomness. The Geary ratio (1954) offered a complementary measure. Local versions—local indicators of spatial association (LISA), developed by Luc Anselin in 1995—identified where clustering occurs, not just whether it exists.
For modelling, the key development was the conditional autoregressive (CAR) and simultaneous autoregressive (SAR) models, which specify a region's value as a function of its neighbours' values plus noise. These were formalized in the 1970s and 1980s, drawing on earlier work in econometrics and geography. The spatial lag and spatial error models became standard in spatial econometrics, a field Anselin helped consolidate in the late 1980s and 1990s, which applies these structures to economic data—house prices, voting, regional growth—where spillovers between neighbouring units are substantively meaningful rather than a nuisance.
Bayesian hierarchical modelling and the smoothing revolution
The 1990s brought a major unification. Bayesian hierarchical models allowed spatial dependence to be represented as a latent random effect with a structured prior—typically a CAR or a Gaussian process—nested within a larger model for the observed data. The Besag–York–Mollié (BYM) model, introduced by Julian Besag, Jeremy York, and Annie Mollié in 1991, became the workhorse for disease mapping: it decomposes each region's relative risk into a spatially structured component and an unstructured heterogeneity component, so that maps of estimated risk are smoothed toward neighbouring values without erasing genuine local spikes.
This framework was computationally demanding, and its spread depended on Markov chain Monte Carlo (MCMC) methods, which became practical in the 1990s. The later development of integrated nested Laplace approximation (INLA) by Håvard Rue and colleagues in 2009 made Bayesian spatial models fast enough for routine use, and the SPDE approach (stochastic partial differential equations) gave a computationally efficient bridge between Gaussian processes and the Markov random fields used in areal models.
Spatially varying coefficients: letting relationships change across space
A parallel development asked not just where values are high but whether the relationship between variables changes across space. Geographically weighted regression (GWR), introduced by Stewart Fotheringham, Chris Brunsdon, and Martin Charlton in the mid-1990s, fits a separate regression at each location, weighting nearby observations more heavily. It produces maps of local coefficients—showing, for example, that the effect of income on house prices differs between neighbourhoods. GWR has been widely used in geography and urban analysis, though it has also drawn criticism for collinearity among local estimates and for the difficulty of inference. Bayesian spatially varying coefficient models, developed in the 2000s, offer an alternative with formal uncertainty quantification.
Machine learning and the present
The most recent turn has been the incorporation of machine learning methods for spatial prediction. Tree-based ensembles, Gaussian process regression, and neural networks can capture nonlinear spatial relationships that kriging and linear models miss, and they scale to large datasets. The tension is that these methods are often black boxes with no built-in notion of spatial dependence; researchers have responded by building spatial features (neighbourhood averages, distances to covariates) into the models, by using random forests with spatial cross-validation to avoid over-optimistic error estimates, and by combining geostatistical covariance structures with flexible learners. Gaussian process regression itself, long central to spatial statistics, has been absorbed into machine learning as a general-purpose Bayesian nonparametric method, so the boundary between the fields is now porous.
Today the main approaches coexist: geostatistical kriging for continuous surfaces, point process models for event locations, areal models and spatial econometrics for regional data, Bayesian hierarchical models for smoothing and uncertainty, and machine learning for flexible prediction at scale. The open questions are familiar in shape but hard in practice: how to do honest inference when the spatial dependence structure is itself estimated, how to combine mechanistic and data-driven models, how to handle massive datasets without losing the uncertainty quantification that made the field worth having, and how to move between the many scales at which spatial processes operate.
References
- Spatial statistics, Wikipedia
- Spatial analysis (Spatial auto-correlation, Spatial dependence), Wikipedia
- Geostatistics (Background), Wikipedia
- Variogram, Wikipedia
The frameworks of Spatial Statistics
Each framework is a way of working the field has used: when it held, and the question it answers.
- 1950-Present
Areal and lattice models
How do neighbouring regions influence each other's values?
- 1950-Present
Point pattern analysis
Are events clustered, regular, or random in space?
- 1960-Present
- 1988-Present
Spatial econometrics
How do economic spillovers between neighbouring units work?
- 1991-Present
Bayesian hierarchical spatial modelling
How can we smooth noisy spatial estimates with uncertainty?
- 1996-Present
Geographically weighted regression
Do relationships between variables change across space?
- 2010-Present
Machine learning for spatial prediction
Can flexible learners capture nonlinear spatial relationships?
How the ideas connect
Each arrow runs from an earlier idea to the later one it shaped. The list below says what passed between them.
Spatial econometrics grew out of Areal and lattice models
Spatial econometrics grew directly out of the areal/lattice tradition: the spatial lag and spatial error models formalized by Luc Anselin and others apply the SAR and CAR structures developed for regional data to economic spillovers. Anselin's 1988 book consolidated this as a distinct field.
Carried by Luc Anselin; Spatial Econometrics: Methods and Models (1988).
Bayesian hierarchical spatial modelling influenced by Areal and lattice models
The Besag–York–Mollié model of 1991 embedded the conditional autoregressive prior from the areal tradition as the spatially structured random effect in a Bayesian hierarchical disease-mapping model. The CAR structure passed directly into the new framework.
Carried by Julian Besag; Besag–York–Mollié model (1991).
Bayesian hierarchical spatial modelling influenced by Geostatistics
Bayesian hierarchical spatial models used Gaussian-process priors, the geostatistical covariance structure, as latent spatial effects alongside the CAR priors taken from areal models. The SPDE approach later gave an explicit computational bridge between Gaussian processes and Markov random fields.
Carried by Håvard Rue; SPDE approach.
Machine learning for spatial prediction influenced by Geostatistics
Machine-learning spatial prediction took the geostatistical covariance structure and kriging framework and combined it with flexible learners, using variogram-based features and Gaussian-process covariance within tree ensembles and neural networks.
Geographically weighted regression influenced by Areal and lattice models
Geographically weighted regression borrowed the areal tradition's concern with local spatial association, fitting separate regressions at each location with distance-based weights in the spirit of local indicators of spatial association.
Carried by Stewart Fotheringham; Chris Brunsdon; Martin Charlton.
Beyond the field
Where Spatial Statistics's ideas came from in other fields, and what they led to there: the strongest 12 of 24 links.
Areal and lattice models influenced by Lattice models and statistical field theory in Statistical Mechanics
The Ising model and lattice statistical mechanics supplied the Gibbs-Markov random field formulation that areal lattice models (Besag's auto-models, 1974) took up directly. The conditional-specification and Markov-random-field machinery passed from statistical physics into spatial lattice statistics.
Carried by Ernst Ising; Julian Besag.
Point pattern analysis influenced by Probability and Stochastic Processes in Applied Mathematics
Probability and stochastic process theory, especially Poisson processes and renewal theory, provided the mathematical foundation of point pattern analysis: the homogeneous Poisson process as the benchmark of complete spatial randomness and the distance distributions derived from it. The later field is built on this stochastic-process base.
Point pattern analysis influenced by Stochastic process in Probability Theory
Stochastic process theory, including Poisson and Markov point processes, is the mathematical basis of point pattern analysis; the Poisson process defines complete spatial randomness and the theory of point processes formalises clustering and inhibition. The statistical field took its core models from this theory.
Bayesian hierarchical spatial modelling influenced Spatial Cluster Detection in Spatial Epidemiology
Bayesian hierarchical spatial modelling provided the smoothed relative-risk estimates and posterior probability measures that cluster detection methods used to identify areas of excess risk. The later tests, such as Bayesian cluster detection, are built on this hierarchical modelling framework.
Carried by Leonhard Held.
Bayesian hierarchical spatial modelling grew out of Bayesian hierarchical modeling in Bayesian Statistics
Bayesian hierarchical spatial modelling is a direct branch of Bayesian hierarchical modelling, adding spatial random effects and conditional autoregressive priors to the multilevel hierarchical framework. The later field generalised the earlier hierarchical model to spatial dependence structures.
Areal and lattice models influenced Spatially Explicit Modeling in Landscape Ecology
Areal and lattice models in spatial statistics, including spatial autocorrelation and lattice Markov methods, provided the formal tools that spatially explicit ecological models used to represent neighbourhood interactions on grids.
Areal and lattice models influenced by Locational Analysis and Spatial Science in Urban Geography
Locational analysis posed the questions of spatial association and pattern in areal units (regions, zones) that early lattice and spatial-autocorrelation work addressed, and its regional data motivated statistics such as Moran's and Geary's measures. The quantitative-spatial-analysis programme supplied the areal data and problems the lattice models formalised.
Carried by Patrick Alfred Pierce Moran.
Areal and lattice models influenced by Design-based and randomization inference in Statistical Inference
Randomization and permutation inference, developed in experimental design, supplied the permutation-based tests of spatial autocorrelation (Moran's and Geary's statistics) used in areal lattice analysis. The null distributions of these spatial statistics were derived by randomization arguments.
Carried by Ronald Aylmer Fisher; Patrick Alfred Pierce Moran.
Areal and lattice models influenced Spatial Cluster Detection in Spatial Epidemiology
Areal and lattice models from spatial statistics supplied the adjacency and autocorrelation structures, such as the Moran and Besag-York-Mollié formulations, on which cluster detection statistics for aggregated regions were built. The later methods depend on these lattice representations.
Carried by Patrick Moran; Julian Besag.
Point pattern analysis influenced by Gaussian process in Stochastic Processes
Gaussian process theory supplied covariance and conditional-intensity machinery used in modelling spatially correlated point and event data, and the Gaussian random field became a standard model for continuous spatial variation underlying point-process intensities. The later point-process literature adopted this covariance-based modelling.
Point pattern analysis influenced by Locational Analysis and Spatial Science in Urban Geography
Locational analysis's concern with the arrangement of points (settlements, facilities) and nearest-neighbour measures fed directly into point pattern analysis, which formalised these questions with distance functions and Poisson benchmarks. The geographic point-data problems shaped the early statistical treatment of point patterns.
Geostatistics influenced Geographic information system in Environmental Assessment
Spatial statistics supplied the autocorrelation, interpolation and point-pattern methods that GIS incorporated as analytical tools. Geostatistical and spatial-statistical estimators were built into GIS software for spatial analysis.

Spatial Statistics is a planet in Nousfarer
Its city has a tower for each of these 7 frameworks. Land, walk in, and climb one concept at a time.
Land on Spatial StatisticsRelated fields
Fields its ideas are linked to
- Spatial Epidemiology 3 links
- Regional Economics 3 links
- Urban Geography 2 links
- Machine Learning 1 link
- Geospatial And Spatial Humanities 1 link
- Geophysics 1 link
- Seismology 1 link
- Landscape Ecology 1 link
- Environmental Assessment 1 link
- Population Geography 1 link
- Applied Mathematics 1 link
- Probability Theory 1 link
More in Statistics
- Bayesian Statistics
- Causal Inference
- Experimental Design
- Multivariate Statistics
- Nonparametric Statistics
- Regression Analysis
- Statistical Computing
- Statistical Inference
- Statistical Learning
- Statistics
- Survey Sampling
- Survival Analysis
- Time Series Analysis
See where Spatial Statistics sits on the Map of Human Knowledge