geoR: varcovBGCCM – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

varcovBGCCM

Covariance matrix for the bivariate Gaussian common component geostatistical model

Description

Covariance matrix for the bivariate Gaussian common component geostatistical model or its inverse, and optionally the determinant of the matrix.

Usage

varcovBGCCM(dists.obj, cov0.pars, cov1.pars, cov2.pars,
            cov0.model = "matern", cov1.model = "matern",
            cov2.model = "matern", kappa0 = 0.5, kappa1 = 0.5,
            kappa2 = 0.5, scaled = TRUE, inv = FALSE, det = FALSE)

Arguments

`dists.obj`	a vector with distance values
`cov0.pars`	covarianve paremeter values for the common component
`cov1.pars`	covariance parameter for the individual structure of the first variable
`cov2.pars`	covariance parameter for the individual structure of the second variable
`cov0.model`	character indicating a valid correlation model
`cov1.model`	character indicating a valid correlation model
`cov2.model`	character indicating a valid correlation model
`kappa0`	scalar
`kappa1`	scalar
`kappa2`	scalar
`scaled`	logical
`inv`	logical. If `TRUE` the inverse of the covariance matrix is returned instead.
`det`	logical. Optional, if `TRUE` the logarithm of the detarminant of the covariance matrix is returned as an attribute.

Value

A matrix which is the covariance matrix for the bivariate Gaussian common component geostatistical model or its inverse if inv=TRUE. If det=T the logarithm of the determinant of the matrix is also returned as an attribute named logdetS.

Warning

This is a new function and still in draft format and pretty much untested.

Author(s)

Paulo J. Ribeiro Jr. paulojus@leg.ufpr.br,
Peter J. Diggle p.diggle@lancaster.ac.uk.

Examples

# see http://www.leg.ufpr.br/geoR/tutorials/CCM.R

geoR

Analysis of Geostatistical Data

v1.8-1

GPL (>= 2)

Authors

Paulo J. Ribeiro Jr [aut, cre] <paulojus@ufpr.br>, Peter J. Diggle [aut, cre] <p.diggle@lancaster.ac.uk> Ole Christensen [ctb], Martin Schlather [ctb], Roger Bivand [ctb], Brian Ripley [ctb]

Initial release

2020-02-08