tests for spatial autocorrelation are designed to quantify the extent of clustering and are measures of similarity between association in value (covariance, correlation, or difference) and association in space (contiguity). A listing of spatial autocorrelation statistics for increasing orders of contiguity is referred to as a spatial correlogram.

The presence of strong relationships among observations taken from points in space. It results in biased regression coefficients. Special statistical techniques, known as Spatial Statistics and Spatial Econometrics, need to be applied to correct the problems associated with spatial autocorrelation.

The degree to which a set of features tend to be clustered together (positive spatial autocorrelation) or be evenly dispersed (negative spatial autocorrelation) over the earth's surface. This is often measured using either Geary's coefficient or Moran's coefficient. When data are spatially autocorrelated the assumption that they are independently random is invalid, so many statistical techniques are invalidated.

A term that refers to patterned variation among spatial phenomena. The great majority of statistical inferential procedures used in archaeological predictive modeling assume independent observations, that is, that the values of some observations cannot be predicted (at a better than random chance) from the known values of other values. Since spatial phenomena generally exhibit patterned variation, or autocorrelation, the assumption of statistical independence is violated. As a result, statistical significance tends to be overestimated. In models of this kind, then, the effect of autocorrelation has to be controlled or at least taken into account.

A situation in which some parameter at any location (e.g., population density) can be predicted through a knowledge of the values of the parameter in other locations.