The VARIOGRAM Procedure

Getting Started

In activities such as reservoir estimation in mining, petroleum exploration, and environmental modeling of air and water pollution, it often happens that data on one or more quantities are available at given spatial locations, and the goal is to predict the measured quantities at unsampled locations. Often, these unsampled locations are on a regular grid, and the predictions are used to produce surface plots or contour maps.

A popular method of spatial prediction is ordinary kriging, which produces both predicted values and associated standard errors. Ordinary kriging requires the complete specification (the form and parameter values) of the spatial dependence of the spatial process in terms of a covariance or semivariogram model.

Typically the semivariogram model is not known in advance and must be estimated, either visually or by some estimation method.

PROC VARIOGRAM computes the sample semivariogram, from which you can find a suitable theoretical semivariogram by visual methods.

The following example goes through a typical problem to show how you can compute a sample variogram and determine an appropriate theoretical model.

Getting Started

Preliminary Spatial Data Analysis

Preliminary Variogram Analysis

Sample Variogram Computation and Plots