Description Usage Arguments Value References See Also Examples
rescale.NIGrid
manipulates a grid for more efficient numerical integration with
respect to a given domain (bounded integral) or vector
of means and covariance matrix (unbounded integral).
1 2 3 4 5 |
object |
an initial grid of type |
... |
further arguments passed to or from other methods |
domain |
a (d x 2)-matrix with the boundaries for each dimension |
m |
vector of means |
C |
covariance matrix |
dec.type |
type of covariance decomposition (Peter Jaeckel (2005)) |
This function modifies the "support-attribute" of the grid. The
recalculation of the nodes and weights is done when the getNodes
or getWeights
are used.
Peter Jaeckel (2005): A note on multivariate Gauss-Hermite quadrature
1 2 3 4 5 6 7 8 9 10 11 12 13 14 | C = matrix(c(2,0.9,0.9,2),2)
m = c(-.5, .3)
par(mfrow=c(3,1))
myGrid <- createNIGrid(dim=2, type="GHe", level=5)
rescale(myGrid, m=m, C=C, dec.type=0)
plot(myGrid, col="red")
rescale(myGrid, m=m, C=C, dec.type=1)
plot(myGrid, col="green")
rescale(myGrid, m=m, C=C, dec.type=2)
plot(myGrid, col="blue")
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.