rfe_sce: Recursive Feature Elimination for SCE Models

In SCE: Stepwise Clustered Ensemble

Recursive Feature Elimination for SCE Models

Description

Recursive Feature Elimination for SCE models to identify the most important predictors.

Usage

rfe_sce(training_data, testing_data, predictors, predictant, nmin, ntree,
        alpha = 0.05, resolution = 1000, step = 1, verbose = TRUE,
        parallel = TRUE)

Arguments

training_data	Training dataset
testing_data	Testing dataset
predictors	Character vector of predictor names
predictant	Character vector of predictant names
nmin	Minimum samples per node
ntree	Number of trees
alpha	Significance level (default: 0.05)
resolution	Resolution for splitting (default: 1000)
step	Number of predictors to remove per iteration (default: 1)
verbose	Print progress (default: TRUE)
parallel	Use parallel processing (default: TRUE)

Value

RFE results with performance metrics and importance scores.

See Also

plot_rfe, sce, importance

SCE documentation built on May 11, 2026, 9:07 a.m.