geospt (version 1.0-4)

rbf.cv1: Generates a RMSPE value, result of cross validation leave-one-out

Description

Generate the RMSPE value, which is given by the radial basis function with smoothing parameter eta and robustness parameter rho.

Usage

rbf.cv1(param, formula, data, n.neigh, func)

Value

returns the RMSPE value

Arguments

param

vector starting points (eta and rho respectively) for searching the RMSPE optimum.

formula

formula that defines the dependent variable as a linear model of independent variables; suppose the dependent variable has name z, for a rbf detrended use z~1, for a rbf with trend, suppose z is linearly dependent on x and y, use the formula z~x+y (linear trend).

data

SpatialPointsDataFrame: should contain the dependent variable, independent variables, and coordinates.

n.neigh

number of nearest observations that should be used for a rbf prediction, where nearest is defined in terms of the spatial locations

func

radial basis function model type, e.g. "GAU", "EXPON", "TRI", "TPS", "CRS", "ST", "IM" and "M", are currently available

See Also

rbf

Examples

if (FALSE) {
data(preci)
coordinates(preci) <- ~x+y
bobyqa(c(0.5, 0.5), rbf.cv1, lower=c(1e-05,0), upper=c(2,2), formula=prec~x+y, data=preci,
    n.neigh=9, func="TRI")
# obtained with the optimal values previously estimated
rbf.cv1(c(0.2126191,0.1454171), prec~x+y, preci, n.neigh=9, func="TRI")  
}