hetGP)Gaussian process predictions using a heterogeneous noise GP object (of class hetGP)
# S3 method for hetGP
predict(object, x, noise.var = FALSE, xprime = NULL, nugs.only = FALSE, ...)list with elements
mean: kriging mean;
sd2: kriging variance (filtered, e.g. without the nugget values)
nugs: noise variance prediction
sd2_var: (returned if noise.var = TRUE) kriging variance of the noise process (i.e., on log-variances if logN = TRUE)
cov: (returned if xprime is given) predictive covariance matrix between x and xprime
an object of class hetGP; e.g., as returned by mleHetGP
matrix of designs locations to predict at (one point per row)
should the variance of the latent variance process be returned?
optional second matrix of predictive locations to obtain the predictive covariance matrix between x and xprime
if TRUE, only return noise variance prediction
no other argument for this method.
The full predictive variance corresponds to the sum of sd2 and nugs.
See mleHetGP for examples.