specifies the input data set that contains
parameter values for the covariance or
semivariogram model. The MDATA= data set must
contain variables named SCALE, RANGE, and FORM,
and it can optionally contain variables NUGGET,
ANGLE, and RATIO.
The FORM variable must be a character variable, assuming
only the values allowed in the
explicit FORM= syntax described previously.
The RANGE and SCALE variables must be numeric.
The optional variables ANGLE, RATIO, and NUGGET
must also be numeric if present.
The number of observations present in the
MDATA= data set corresponds to the level
of nesting of the
semivariogram model.
For example, to
specify a nonnested model using a
spherical covariance, an MDATA= data
set might look like
data md1;
input scale range form $;
datalines;
25 10 SPH
run;
The PROC KRIGE2D statement to use the
MDATA= specification is of the form
proc krige2d data=...;
pred var=....;
model mdata=md1;
run;
This is equivalent
to the following explicit specification of the
covariance model parameters:
proc krige2d data=...;
pred var=....;
model scale=25 range=10 form=sph;
run;
The following MDATA= data set
is an example of an anisotropic nested model:
data md1;
input scale range form $ nugget angle ratio;
datalines;
20 8 S 5 35 0.7
12 3 G 5 0 0.8
4 1 G 5 45 0.5
;
This is equivalent
to the following explicit specification of the
covariance model parameters:
proc krige2d data=...;
pred var=....;
model scale=(20,12,4) range=(8,3,1) form=(S,G,G)
angle=(35,0,45) ratio=(0.7,0.8,0.5) nugget=5;
run;
This example is somewhat artificial in that it is
usually hard to detect different anisotropy directions and
ratios
for different nestings using an experimental semivariogram.
Note that the NUGGET value is the same for all nestings. This
is always the case; the nugget effect is a single additive
term for all models. For further details,
see the section "Theoretical and Computational Details of the Semivariogram" in the chapter on
the VARIOGRAM procedure.