The KRIGE2D Procedure

Syntax: KRIGE2D Procedure

The following statements are available in the KRIGE2D procedure:

The PREDICT and MODEL statements are hierarchical; the PREDICT statement is followed by a MODEL statement. If more than one MODEL statement is given, only the last one is used for the analysis. The MODEL statement following a PREDICT statement uses the variable and neighborhood specifications in that PREDICT statement.

You must specify at least one PREDICT statement and one MODEL statement. You must supply a single COORDINATES statement to identify the x and y coordinate variables in the input data set. You must also specify a single GRID statement to include the grid information.

Table 55.1 outlines the options available in PROC KRIGE2D classified by function.

Table 55.1: Options Available in the KRIGE2D Procedure

Task

Statement

Option

Data Set Options

   

Specifies input data set

PROC KRIGE2D

DATA=

Specifies grid data set

GRID

GDATA=

Specifies labels for individual grid points or in 1-D

GRID

LABEL

Specifies model data set

MODEL

MDATA=

Writes kriging predictions and standard errors

PROC KRIGE2D

OUTEST=

Writes neighborhood information for each grid point

PROC KRIGE2D

OUTNBHD=

Specifies plot display and options

PROC KRIGE2D

PLOTS

Declaring the Role of Variables

   

Specifies variables to define analysis subgroups

BY

 

Specifies variable with observation labels

ID

 

Specifies the variables to be predicted (kriged)

PREDICT

VAR=

Specifies the x and y coordinate variables in the DATA= data set

COORDINATES

XC= YC=

Specifies the x and y coordinate variables in the GDATA= data set

GRID

XC= YC=

Controlling the Prediction

   

Specifies the number of grid points in one-dimensional cases

GRID

NPTS=

Controlling Kriging Neighborhoods

   

Specifies the radius of a neighborhood for all grid points

PREDICT

RADIUS=

Specifies the number of neighbors for all grid points

PREDICT

NUMPOINTS=

Specifies the maximum of neighbors for all grid points

PREDICT

MAXPOINTS=

Specifies the minimum of neighbors for all grid points

PREDICT

MINPOINTS=

Specifies the action when maximum not met

PREDICT

NODECREMENT

Specifies the action when minimum not met

PREDICT

NOINCREMENT

Controlling the Semivariogram Model

   

Specifies an angle for an anisotropic model

MODEL

ANGLE=

Specifies a type with a functional form

MODEL

FORM=

Specifies an item store with correlation information

RESTORE

IN=

Specifies a nugget effect

MODEL

NUGGET=

Allows power exponent values outside [0,2)

MODEL

POWNOBOUND

Specifies a range parameter

MODEL

RANGE=

Specifies a minor-major axis ratio for an anisotropic model

MODEL

RATIO=

Specifies a scale parameter

MODEL

SCALE=

Specifies model and parameters from an item store

MODEL

STORESELECT