kmNuggets.init {DiceKriging} | R Documentation |
kmNuggets.init
is used to give initial values to fit kriging models, in presence of noisy observations.
kmNuggets.init(model)
model |
an object of class km . |
The procedure can be summarized in 4 stages:
1) | Compute the variogram and give a first estimation of the process variance, as well as lower and upper bounds. |
2) | Simulate several values for the process variance, around the estimation obtained at stage 1). The number of simulations is the one given in model@control$pop.size . |
3) | If no initial value is provided for the other covariance parameters, simulate them uniformly inside the domain delimited by model@lower and model@upper . The number of simulations is the same as in stage 2). |
4) | Compute the likelihood at each simulated "point" (variance + other covariance parameters), and take the best one. This point gives the first initial values. |
An object of class km
.
O. Roustant, David Ginsbourger, Ecole des Mines de St-Etienne.