weighted_clr: Weighted CLR Transform

In jsilve24/philr: Phylogenetic partitioning based ILR transform for metagenomics data

Weighted CLR Transform

Description

Weighted CLR Transform

Usage

clrp(y, p)

clrpInv(y.star)

Arguments

y	shifted data matrix (e.g., output of shiftp)
p	weights (should not be closed)
y.star	a data matrix that represents data transformed by clrp

Details

Note that this function will close the dataset y to 1.

Inverting clrp transform should be followed by shiftpInv to return to unshifted original compositoin (see examples).

Value

matrix

Author(s)

Justin Silverman

References

J. J. Egozcue, V. Pawlowsky-Glahn (2016) Changing the Reference Measure in the Simplex and its Weighting Effects. Austrian Journal of Statistics 45(4):25-44

Examples

p <- seq(.1,1,by=.2)
c <- t(rmultinom(10,100,c(.1,.6,.2,.3,.2))) + 0.65   # add a small pseudocount
x <- miniclo(c)
y <- shiftp(x, p)
y.star <- clrp(y, p)
y.star

# Untransform data (note use of shiftp and miniclo to return to x)
y.closed <- clrpInv(y.star)
all.equal(miniclo(shiftpInv(y.closed, p)), x)

jsilve24/philr documentation built on Oct. 17, 2024, 4:59 p.m.