dk {RGeostats}R Documentation

Performs Disjunctive Kriging


Disjunctive Kriging


dk(dbin, dbgrid, model = model.input(), neigh = neigh.input(), 
   nmult=NA, ndisc = NA, nfactor=NA, flag.est = TRUE, flag.std = TRUE, 
   radix = "DK", = db.locmod())



The db-class structure containing the data file


The db-class structure containing the target file. It must be organized as a regular grid. It corresponds either to the grid SMU or directly to the grid of panels. In the latter case, the way a panel is partioned into a set of SMU must be specified through the argument 'nmult'.


The model-class structure containing the Model information. The model must contain some Anamorphosis Transformation. The Anamorphosis (transported through this 'model' argument) tells the system if the user is about to calculate, via a Disjunctive Kriging of the Factors:

  • the average grade and tonnage per SMU (for a Point Anamorphosis. In this case, the argument 'ndisc'which specifies the way a block is discretized is mandatory.)

  • the proportion of SMU within a Panel (for a Block Anamorphosis)


The neigh-class structure containing the Neighborhood information


When a Block Anamorphosis is specified (through the 'model' argument), the user can calculate the Q,T results either on each SMU (the argument 'dbgrid' then corresponds to the grid of SMUs) or directly on each panel. In the latter case, the argument 'dbgrid' is the grid of panels and the argument 'nmult' defines the way a panel is partitioned in SMUs.


Array giving the number of discretisation points in each direction of the space. If the dimension of the argument 'ndisc' does not match the space dimension, this vector is set to 1 in each direction, leading to a point estimation. This discretization is used when the block average of the discretized grade is calculated using the Disjunctive Kriging approach.


The number of factors that must be estimated. This number must be smaller than the number of classes in the Discrete Anamorphosis. If undefined, all the factors will be treated.


When TRUE, the estimations are required: the estimation of all active factors as well as the reconstructed discretized grade.


When TRUE, the standard deviation of estimations are required: the standard deviation of all active factors as well as the reconstructed discretized grade.


Radix of the name given to the variables storing the results in the target Db.

Decides whether or not the newly created variables will have their locator defined or not. For more information, see db.locmod.


The target Db where the following variables have been added:

[Package RGeostats version 11.0.6 Index]