DirichletRF: Dirichlet Random Forest
Implementation of the Dirichlet Random Forest algorithm
for compositional response data. Trees are grown using a Dirichlet
log-likelihood splitting criterion, with maximum likelihood ('MLE') and
method-of-moments ('MOM') parameter estimation. Provides averaging-based
predictions (average of responses within terminal nodes), parameter-based
predictions (expected value derived from the estimated Dirichlet
parameters within terminal nodes), and distributional predictions
represented as a weighted distribution over the training responses.
Out-of-bag estimation and impurity- and permutation-based variable
importance are also supported. For more details see Masoumifard, van der
Westhuizen, and Gardner-Lubbe (2026, ISBN:9781032903910).
Documentation:
Downloads:
Linking:
Please use the canonical form
https://CRAN.R-project.org/package=DirichletRF
to link to this page.
[aut, cre],
Stephan van der Westhuizen