Inverse distance weighting

Inverse distance weighting, abbreviated IDW, is a deterministic method of multivariate interpolation for a set of known, homogeneously scattered points. The value assigned to an unknown point is a weighted average of the values available at the known points, and the weight of each known point is based on the inverse of its distance, the amount of proximity, which gives the method its name. Nearer known points therefore influence the estimate more than distant ones. Beyond interpolation, the same weighting idea can be used to create spatial weights matrices in spatial autocorrelation analyses, for example for Moran's I. The method is valued for being simple to state and to compute.