compositions (version 2.0-4)

rcompmargin: Marginal compositions in real geometry

Description

Compute marginal compositions by amalgamating the rest (additively).

Usage

rcompmargin(X,d=c(1,2),name="+",pos=length(d)+1,what="data")

Value

A closed compositions with class "rcomp" containing the selected variables given by d and the the amalgamation column.

Arguments

X

composition or dataset of compositions

d

vector containing the indices xor names of the columns to be kept

name

The new name of the amalgamation column

pos

The position where the new amalgamation column should be stored. This defaults to the last column.

what

The role of X either "data" for data (or means) to be transformed or "var" for variances to be transformed.

Author

K.Gerald v.d. Boogaart http://www.stat.boogaart.de, Raimon olosana-Delgado

Missing Policy

MNAR has the highest priority, MAR next and WZERO (BDL,SZ),- values are considered as 0 and reported as BDL in the End.

Details

The amalgamation column is simply computed by adding the non-selected components after closing the composition. This is consistent with the rcomp approach and is widely used because of its easy interpretation. However, it often leads to difficult-to-read ternary diagrams and is inconsistent with the acomp approach.

With the argument what="var" the function transformes an rcomp variance to the resulting variance of the resulting composition.

References

References missing

See Also

acompmargin, rcomp

Examples

data(SimulatedAmounts)
plot.rcomp(sa.tnormals5,margin="rcomp")
plot.rcomp(rcompmargin(sa.tnormals5,c("Cd","Zn")))
plot.rcomp(rcompmargin(sa.tnormals5,c(1,2)))