Ordinary Kriging

Ordinary kriging (OK) is a geostatistical approach to modeling. Instead of weighting nearby data points by some power of their inverted distance, OK relies on the spatial correlation structure of the data to determine the weighting values. This is a more rigorous approach to modeling, as correlation between data points determines the estimated value at an unsampled point. The concept of spatial correlation and how to measure and model it in your data set is briefly described in Spatial Correlation and Modeling Spatial Correlation. Furthermore, OK makes the assumption of normality among the data points. (See Setting Normality/Lognormality Assumption.)

In addition to the spatial correlation structure, SADA requires a definition of the neighborhood around estimation points. The issue of neighborhood definition is important to inverse distance and indicator kriging, as well. For this reason, a discussion of neighborhood definitions is consolidated in Defining A Neighborhood.

Because OK is a statistical framework, a kriging variance is also produced for each block that can be viewed with the **Variance **Map button** **on the main toolbar. The OK estimate and variance are the parameters of a normal distribution located at the estimation point that can *serve as a measure* of uncertainty about the estimated value. This serves as an important foundation for decision frameworks that determine cost and boundaries of the remedial process. See Overview of Decision Frameworks.

A full explanation of ordinary kriging is beyond the scope of this manual. It is assumed that the reader is familiar with the process. For information on ordinary kriging see *GSLIB Geostatistical Software Library and User’s Guide* by Deutsch and Journel (1992) or *An Introduction to Applied Statistics* by Isaaks and Srivastava.

To utilize ordinary kriging, the Spatial Correlation model for the contaminant of interest must be developed and a neighborhood must be defined in the **Geo **tab of the **Control Panel**. Then SADA will be prepared to use OK in all of its mapping functions.