Using disjunctive kriging to create a prediction standard error map

Available with Geostatistical Analyst license.

A standard error map quantifies the uncertainty of the prediction. If the data comes from a normal distribution, the true value will be within ± 2 times the prediction standard errors approximately 95 percent of the time.

1. Start the Geostatistical Analyst Wizard .
2. Select Kriging/CoKriging, choose a dataset and attribute field, then click Next.
3. Choose Disjunctive, set the Transformation type to Normal Score, set the Output Type to Prediction Standard Error, then click Next.
4. Specify the desired parameters on the Normal Score Transformation dialog box and click Next.
5. Specify the desired parameters on the Semivariogram/Covariance Modeling dialog box and click Next.
6. Specify the desired parameters on the Searching Neighborhood dialog box and click Next.
7. Examine the results on the Cross Validation dialog box and click Finish.
8. Click OK on the Method Report dialog box.