plot.MFPCAfit function

Plot MFPCA results

Plots the eigenfunctions as perturbations of the mean (i.e. the mean function plus/minus a constant factor times each eigenfunction separately). If all elements have a one-dimensional domain, the plots can be combined, otherwise the effects of adding and subtracting are shown in two separate rows for each eigenfunction.

## S3 method for class 'MFPCAfit'
plot(
  x,
  plotPCs = seq_len(nObs(x$functions)),
  stretchFactor = NULL,
  combined = FALSE,
  ...
)

Arguments

• x: An object of class MFPCAfit, typically returned by the MFPCA function.
• plotPCs: The principal components to be plotted. Defaults to all components in the MFPCAfit object.
• stretchFactor: The factor by which the principal components are multiplied before adding / subtracting them from the mean function. If NULL (the default), the median absolute value of the scores of each eigenfunction is used.
• combined: Logical: Should the plots be combined? (Works only if all dimensions are one-dimensional). Defaults to FALSE.
• ...: Further graphical parameters passed to the plot.funData functions for functional data.

Returns

A plot of the principal components as perturbations of the mean.

Examples

# Simulate multivariate functional data on one-dimensonal domains
# and calculate MFPCA (cf. MFPCA help)
set.seed(1)
# simulate data (one-dimensional domains)
sim <-  simMultiFunData(type = "split", argvals = list(seq(0,1,0.01), seq(-0.5,0.5,0.02)),
                       M = 5, eFunType = "Poly", eValType = "linear", N = 100)
# MFPCA based on univariate FPCA
PCA <- MFPCA(sim$simData, M = 5, uniExpansions = list(list(type = "uFPCA"),
                                                     list(type = "uFPCA")))

# Plot the results
plot(PCA, combined = TRUE) # combine addition and subtraction in one plot

See Also

MFPCA, plot.funData