ilr.stab: Compute the Robust ilr Stability for Two Parts of a Composition

Description

Function computes the Robust ilr Stability for two parts of a composition following the procedure in Filzmoser et al. (2010), see details below.

Usage

ilr.stab(xx1, xx2, ifwarn = T)

Arguments

xx1

a column vector from a matrix or data frame of compositional data, xx1[1], ..., xx1[n].

xx2

another column vector from the matrix or data frame of compositional data, xx2[1], ..., xx2[n]. xx1 and xx2 must be of identical length, n.

ifwarn

by default ifwarn = TRUE which generates a reminder/warning that when carrying out analyses of compositional data all data must be in the same measurement units. The message can be suppressed by setting ifwarn = FALSE.

Details

The ilr transform of two parts of a composition is ilr.xy = 1/(sqrt(2)) * log(x1/x2). The Robust ilr Stability (Filzmoser et al., 2010) is computed from the MAD of the ilr.xy values. This is normalized into the (0,1) interval as exp(-ilr.MAD * ilr.MAD), following the procedure of Buccianti and Pawlowsky-Glahn (2005).

References

Buccianti, a. and Pawlowsky-Glahn, V., 2005. New perspectives on water chemistry and compositional data analysis. Mathematical Geology, 37(7):703-727.

Filzmoser, P, Hron, K. and Reimann, C., 2010. The bivariate statistical analysis of environmental (compositional) data. Science of the Total Environment, 408(19):4230-4238.

Examples

Run this code

# NOT RUN {
## Make test data available
data(sind)
attach(sind)

## Compute Robust ilr Stability
ilr.stab(Cu, Zn)

## Detach test data
detach(sind)
# }