alr: alr The additive log-ratio transformation

In zdk123/compPLS: Conduct Partial Least Squares regression for compositional data

alr The additive log-ratio transformation

Description

The additive log-ratio transformation for compositional data (not necessarily closed/normalized!)

Usage

alr(x, ...)

## Default S3 method:
alr(
  x,
  divcomp = 1,
  base = exp(1),
  removeDivComp = TRUE,
  tol = .Machine$double.eps
)

## S3 method for class 'matrix'
alr(
  x,
  mar = 2,
  divcomp = 1,
  base = exp(1),
  removeDivComp = TRUE,
  tol = .Machine$double.eps
)

## S3 method for class 'data.frame'
alr(x, mar = 2, ...)

Arguments

x	a numeric data vector containing components of a composition
...	additional arguments
divcomp	index of the divisor component
base	base of log to use, default is natural log
removeDivComp	remove divisor component from the resulting data
tol	machine tolerance for a zero count, default is machine tol (.Machine$double.eps)

Details

The alr transformation is computed as: x[i] = log ( x[i] / x[D] )

Value

alr transformed x

Examples

# vector examples:
alr(norm_to_total(1:10))
alr(1:10)

# matrix examples:
dmat <- matrix(exp(rnorm(110)), 10)
alr(dmat, 1)
alr(dmat, 2)

zdk123/compPLS documentation built on April 24, 2022, 2:44 p.m.