pb_basis {coda.base}

Isometric log-ratio basis based on Principal Balances.

Description

Exact method to calculate the principal balances of a compositional dataset. Different methods to approximate the principal balances of a compositional dataset are also included.

Usage

pb_basis(
  X,
  method,
  constrained.complete_up = FALSE,
  cluster.method = "ward.D2",
  ordering = TRUE,
  ...
)

Arguments

X

compositional dataset

method

method to be used with Principal Balances. Methods available are: 'exact', 'constrained' or 'cluster'.

constrained.complete_up

When searching up, should the algorithm try to find possible siblings for the current balance (TRUE) or build a parent directly forcing current balance to be part of the next balance (default: FALSE). While the first is more exhaustive and given better results the second is faster and can be used with highe dimensional datasets.

cluster.method

Method to be used with the hclust function (default: 'ward.D2') or any other method available in hclust function

ordering

should the principal balances found be returned ordered? (first column, first principal balance and so on)

...

parameters passed to hclust function

Value

matrix

References

Martín-Fernández, J.A., Pawlowsky-Glahn, V., Egozcue, J.J., Tolosana-Delgado R. (2018). Advances in Principal Balances for Compositional Data. Mathematical Geosciencies, 50, 273-298.

Examples

set.seed(1)
X = matrix(exp(rnorm(5*100)), nrow=100, ncol=5)

# Optimal variance obtained with Principal components
(v1 <- apply(coordinates(X, 'pc'), 2, var))
# Optimal variance obtained with Principal balances
(v2 <- apply(coordinates(X,pb_basis(X, method='exact')), 2, var))
# Solution obtained using constrained method
(v3 <- apply(coordinates(X,pb_basis(X, method='constrained')), 2, var))
# Solution obtained using Ward method
(v4 <- apply(coordinates(X,pb_basis(X, method='cluster')), 2, var))

# Plotting the variances
barplot(rbind(v1,v2,v3,v4), beside = TRUE, ylim = c(0,2),
        legend = c('Principal Components','PB (Exact method)',
                   'PB (Constrained)','PB (Ward approximation)'),
        names = paste0('Comp.', 1:4), args.legend = list(cex = 0.8), ylab = 'Variance')