Geostatistical Analyst のライセンスで利用可能。
Use probability kriging to produce a probability or standard error of indicators map. The data points need to be sampled from a phenomenon that is continuous in space, for example, temperature or air quality measurements.
Important parameters are the specified threshold (which determines which predictions will receive a 0 and which will receive a 1), covariance/semivariogram models, and search neighborhoods establishing the model. Estimation of semivariogram/covariance becomes difficult when the indicator variables are primarily all zeros or all ones. If possible, choose a threshold that gives a mix of zeros and ones.
- Click the Geostatistical Analyst Wizard button on the Geostatistical Analyst toolbar.
- Select Kriging/CoKriging, choose a dataset and attribute field, then click Next.
- Choose Probability kriging.
- Set Output type to Probability.
- Type the Threshold value or click the Set button and set the threshold on the Classification dialog box.
- Click either the Exceed or NOT Exceed option and click Next.
- Specify the desired parameters on the Semivariogram/Covariance Modeling dialog box and click Next.
- Specify the desired parameters on the Searching Neighborhood dialog box and click Next.
- Examine the results on the Cross Validation dialog box and click Finish.
- Click OK on the Method Report dialog box.