Spatial Statistics
Spatial statistics deals with spatial data. There are two fundamentally different views. The first involves a continuous value associated with each spatial point, e.g. temperature, elevation or ozone concentration. In this case, spatial estimation of the value anywhere is a key task. The second view involves the spatial point as an event, e.g. tree location, earthquake location or crime location. In this case, getting statistical measures of center, density and homogeneity of the point locations are key tasks.
The Wolfram Language provides a full suite of tools for spatial statistics, including highly automated spatial estimation for random fields and extensive point pattern analysis and modeling.
Continuous Spatial Estimation »
SpatialEstimate — gives a function that can be used to estimate values
VariogramFunction ▪ SpatialTrendFunction ▪ SpatialNoiseLevel ▪ SpatialEstimatorFunction
Spatial Point Collections »
SpatialPointData — create and represent spatial point configurations
SpatialRandomnessTest — test whether a point configuration is uniformly distributed
Center, Density and Homogeneity Measures
SpatialMedian — location in region with minimum distance to all points
Mean ▪ Median ▪ CentralFeature ▪ ...
PointDensity — varying point density function
HistogramPointDensity ▪ SmoothPointDensity ▪ MeanPointDensity
NearestNeighborG — probability of finding another point within distance r of a point
RipleyK ▪ EmptySpaceF ▪ PairCorrelationG ▪ ...
Spatial Point Processes »
RandomPointConfiguration — simulate a point process to give a point collection
EstimatedPointProcess — estimate a point process from spatial point configurations
PointProcessFitTest — test whether data follows a point process
Independent, Interaction and Clustered Point Processes
PoissonPointProcess — constant density of independent points
InhomogeneousPoissonPointProcess ▪ BinomialPointProcess
HardcorePointProcess — constant density of points; no points within radius r of each other
StraussPointProcess ▪ GibbsPointProcess ▪ ...
MaternPointProcess — constant density of center points, with uniform distribution of cluster points in a disk of radius r around each center