make_dyn_cov: Parametrize dynamical covariance structure using Cholesky...

In naolsen/simm.fda: Simultaneous inference for Misaligned Functional Data

Parametrize dynamical covariance structure using Cholesky decomposition

Description

Cholesky decomposition is the recommended way of parametrising the positive definite matrices used for dynamical covariance structure. This function provides a handy wrapper for doing this.

Usage

make_dyn_cov(timefunction, knots, K)

Arguments

timefunction	Time function for dynamical covariance
knots	knots for dynamical covariance
K	Dimension

Details

.

Value

A function

See Also

kovMat

Examples

g <- make_dyn_cov(Materntid, c(0, 0.5, 1), 3)

# assume we have some parameters in a vector pars, e.g. pars = c(rep(c(1,0,0, 1,0,1), 3), 0.1, 1.5) (diagonal covariance)
g(ti, param = pars[1:18], range = pars[19], smooth = pars[20], noise = 1)

naolsen/simm.fda documentation built on June 28, 2022, 2:41 a.m.