This function performs multiple independent K-fold cross-validations to assess the variability in subgroup identification. Each simulation:
Randomly shuffles the data
Performs K-fold CV
Records sensitivity and agreement metrics
Results are summarized across all simulations.
forestsearch_tenfold(
fs.est,
sims,
Kfolds = 10,
details = TRUE,
seed = 8316951L,
parallel_args = list(plan = "multisession", workers = 6, show_message = TRUE)
)List with components:
Named vector of median sensitivity metrics across simulations
Named vector of median subgroup-finding metrics
Matrix of sensitivity metrics (sims x metrics)
Matrix of finding metrics (sims x metrics)
Total execution time
Number of simulations run
Number of folds per simulation
List. ForestSearch results object from forestsearch.
Integer. Number of simulation repetitions.
Integer. Number of folds per simulation (default: 10).
Logical. Print progress details (default: TRUE).
Integer. Base random seed for fold shuffling. Default 8316951L. Each simulation uses seed + 1000 * ksim for reproducibility.
List. Parallelization configuration.
Unlike the single K-fold function which parallelizes across folds, this function parallelizes across simulations for better efficiency when running many repetitions. Each simulation runs its K-fold CV sequentially.
Runs repeated K-fold cross-validation simulations for ForestSearch and summarizes subgroup identification stability across repetitions.
forestsearch_Kfold for single K-fold CV
forestsearch_KfoldOut for summarizing CV results