The methods for analyzing data in one dimension (usually time) are highly developed. In several dimensions, however, most applied workers use only one class of methods: that in which the data are assumed to be the sum of a deterministic trend and an uncorrelated random error. The more general model with a spatially correlated error has been neglected in most fields, oceanography being a conspicuous exception. This neglect is due partly to the lack of expositions for the applied workers. However, the manner in which much geological data are now collected does make this application difficult.