Data characterized by spatial dependence and spatial heterogeneity. Spatial dependence exists when the structure of dependence between random variables is determined by the relative position of observations in the underlying space, which could be a physical space or a network. The extent of the spatial dependence can be characterized by spatial autocorrelation. A specific spatial structure can suggest a particular form of spatial heterogeneity, such as heteroscedasticity, spatial structural breaks, or spatially varying model parameters.