admix (version 2.1-3)

sim_gaussianProcess: Simulation of a Gaussian process

Description

Simulate the trajectory of a Gaussian process, given a mean vector and a variance-covariance structure.

Usage

sim_gaussianProcess(
  mean_vec,
  varCov_mat,
  from = 0,
  to = 1,
  start = 0,
  nb.points = 10
)

Value

The trajectory of the Gaussian processes after simulating the multivariate Gaussian distributions with specified variance-covariance structure.

Arguments

mean_vec

Vector (if multimensional) of means for the increments following gaussian distribution.

varCov_mat

Corresponding variance-covariance structure.

from

Initial time point at which the process is simulated.

to

Last time point at which the process is simulated.

start

Useful if the user wants to make the trajectory start from some given value.

nb.points

Number of points at which the process is simulated.

Author

Xavier Milhaud

Examples

list.comp <- list(f1 = "norm", g1 = "norm")
list.param <- list(f1 = list(mean = 12, sd = 0.4),
                   g1 = list(mean = 16, sd = 0.7))
sample1 <- rsimmix(n = 2000, unknownComp_weight = 0.5, comp.dist = list.comp,
                   comp.param = list.param)$mixt.data
## First get the variance-covariance matrix of the empirical process (Donsker correlation):
cov_mat <- .Call('_admix_estimVarCov_empProcess_Rcpp', PACKAGE = 'admix',
                  seq(from = min(sample1), to = max(sample1), length.out = 100), sample1)
## Plug it into the simulation of the gaussian process:
B1 <- sim_gaussianProcess(mean_vec=rep(0,nrow(cov_mat)), varCov_mat=cov_mat, from=min(sample1),
                          to = max(sample1), start = 0, nb.points = nrow(cov_mat))
plot(x = B1$dates, y = B1$traj1, type="l", xlim = c(min(sample1),max(sample1)), ylim = c(-1,1))