Estimates component component of a nested covariance by
\(\lambda' z\) under \(\sum\lambda = 0\): \(C\lambda + \mu 1 =
c_{k,0}\), variance \(C_k(0) - \lambda' c_{k,0}\) (Wackernagel 2003,
chapter 14; Goovaerts 1997, section 5.6).
Usage
FactorialKrige(z, coords, new_coords, model, component)
Arguments
- z
Observations.
- coords
Matrix of locations (any dimension).
- new_coords
Matrix of targets (block centres with block).
- model
Covariance model (KrigingCovariance).
- component
Index (1-based) of the component to estimate.
Value
List with prediction and variance.
References
Goovaerts, P. (1997). Geostatistics for Natural Resources
Evaluation. Oxford University Press, New York.
Examples
m <- list(list(model = "Exp", psill = 1, range = 1), list(model = "Sph", psill = 0.5, range = 4))
FactorialKrige(c(1, 3, 2, 2.5), rbind(c(0, 0), c(2, 0), c(0, 2), c(2, 2)), rbind(c(0.5, 0.2)), m, 2)
#> $prediction
#> [1] -0.1751326
#>
#> $variance
#> [1] 0.466087
#>
