sort_components

numeric vector.
The vector contains observed assemblage performances.

fobs

a matrix of occurrence of components within the assemblages.
<code>dim(mOccur)[1] = length(fobs)</code>.
<code>dim(mOccur)[2]</code> equals to the total number of components.

mOccur

an integer vector of <code>length(fobs)</code>.
The vector contains a colour label for each assemblages.

cols

a probability,
used as threshold
in the variance analysis. Then <code>pvalue</code> must be
higher than <code>0</code> and lower than <code>1</code>.
Groups significantly different
(at a p-value &lt; <code>pvalue</code>) are then indicated by differents letters
on the right of boxplots.

pvalue

a logical.
If <code>opt.dec = TRUE</code>,
assembly motifs are sorted by decreasing mean performances.
If <code>opt.dec = FALSE</code>,
assembly motifs are sorted by increasing mean performances.

opt.dec

internal

Cluster together the components that make up an interactive
system on the basis of their functional redundancy
for one or more collective, systemic performances.
Plot the hierarchical tree of component clusters,
the modelled and predicted performances of component assemblages,
and other results associated with a functional clustering.
Test and prioritize the significance of the different components
that make up the interactive system,
of the different assemblages of components that make up the dataset,
and of the different performances observed on the component assemblages.
The method finds application in ecology, for instance,
where the system is an ecosystem, the components are organisms or species,
and the systemic performance is the production of biomass
or the respiration of the ecosystem.
The method is extensively described in
Jaillard B, Deleporte P, Loreau M, Violle C (2018)
"A combinatorial analysis using observational data identifies species
that govern ecosystem functioning"
<doi:10.1371/journal.pone.0201135>.

sort_components: Sort assembly centroids by decreasing or increasing mean performances

Description

Usage

Arguments

Value

Details