This function calculates the out-of-bag (OOB) validation predictions for an SCE model. OOB predictions are made using only the trees that did not use a particular observation during training, providing an unbiased estimate of the model's performance.
OOB_validation(model)A data.frame containing the OOB predictions for each predictant. The number of rows equals the number of training samples, and the columns correspond to the predictant variables.
A trained SCE model object generated through the SCE function.
The model must contain OOB information in its Tree_Info component.
Kailong Li <lkl98509509@gmail.com>
The OOB validation process involves:
Extracting OOB indices and predictions from each tree
Weighting the predictions based on tree weights
Calculating weighted means for each sample
This function is typically called internally by Model_simulation
and is not usually called directly by users.
SCE