fd2coef {onlinePCA}

Compute the coefficients of functional data in a B-spline basis

Description

This function computes the coefficients of functional data in a B-spline basis.

Usage

fd2coef(x, basis, byrow = TRUE)

Arguments

x

matrix of functional data.

basis

object created by create.basis

.

byrow

are the functional data stored in rows (TRUE) or in columns (FALSE)?

Value

A matrix of B-spline coefficients stored in the same format (row or columns) as functional data.

Note

In view of (online or offline) functional PCA, the coefficients are smoothed and premultiplied by M^{1/2}, with M the Gram matrix associated to the B-spline matrix.

See Also

create.basis, coef2fd

Examples

n <- 100 # number of curves
d <- 500 # number of observation points
grid <- (1:d)/d # observation points
p <- 50 # number of B-spline basis functions 

# Simulate Brownian motion
x <- matrix(rnorm(n*d,sd=1/sqrt(d)),n,d)
x <- t(apply(x,1,cumsum))

# Create B-spline basis 
mybasis <- create.basis(grid, p, 1e-4)

# Compute smooth basis coefficients 
beta <- fd2coef(x, mybasis)

# Recover smooth functional data
x.smooth <- coef2fd(beta, mybasis) 
	
# Standard PCA and Functional PCA
pca <- prcomp(x)
fpca <- prcomp(beta)