potential.xvalid {RGeostats} | R Documentation |
Perform the Cross-Validation in the Potential Framework
potential.xvalid(db, dbgrd, dbtgt = NA, model = model.input(), neigh = neigh.input(), degree = 0, nugget.grd = 0, nugget.tgt=0, flag.dist.conv=FALSE, verbose = FALSE, radix = "Xvalid", modify.target = db.locmod())
db |
The |
dbgrd |
The |
dbtgt |
The |
model |
The
An additional nugget effect is also authorized. |
neigh |
The |
degree |
Degree of the Intrinsic Random Function used to describe the Potential Random Variable. Note that the degree must be 2 if the model contains the 2nd order Spline Generalized Covariance. |
nugget.grd |
The value of the nugget effect on the Gradient component |
nugget.tgt |
The value of the nugget effect on the Tangent component |
flag.dist.conv |
When TRUE the validation error must be converted into distance. |
verbose |
Verbose option. If switched ON, the procedure displays the mean and variance of the cross-validation error and standardized error. |
radix |
Radix of the name given to the variables storing the results in the target Db. |
modify.target |
Decides whether or not the newly created variables will have their
locator defined or not. For more information, see |
The target Db where the following variables have been added:
the mean error
the mean variance
the mean euclidean distance
the mean distance along surface
The last two variables are produced only if 'flag.dist.conv' is ON.