MJMbamlss (version 0.1.0)

attach_wfpc: Attach Weighted Functional Principal Components to the Data

Description

Attach Weighted Functional Principal Components to the Data

Usage

attach_wfpc(
  mfpca,
  data,
  n = NULL,
  obstime = "obstime",
  marker = "marker",
  eval_weight = FALSE
)

Value

Data set supplied as argument data with additional columns corresponding to the evaluations of the MFPC basis.

Arguments

mfpca

MFPCA object from which to extract the weighted FPCS.

data

Data set to which the weighted FPCS are to be attached.

n

Number of FPCs to attach. Defaults to NULL which corresponds to all FPCs in mfpc.

obstime

Name of the time variable in data set at which points to evaluate.

marker

Name of the marker variable in the data set which separates the data.

eval_weight

Weight the FPC by the square root of its eigenvalue (then variance comparable throughout all FPCs). Defaults to FALSE.

Examples

# Small example based on subset of PBC data
data(pbc_subset)

# Estimate MFPC basis and attach to data
mfpca <- preproc_MFPCA(pbc_subset, uni_mean = paste0(
    "logy ~ 1 + sex + drug + s(obstime, k = 5, bs = 'ps') + ",
    "s(age, k = 5, bs = 'ps')"),
    pve_uni = 0.99, nbasis = 5, weights = TRUE, save_uniFPCA = TRUE)
pbc_subset <- attach_wfpc(mfpca, pbc_subset, n = 2)