control.errorest {ipred}R Documentation

Control Error Rate Estimators

Description

Some parameters that control the behaviour of errorest.

Usage

control.errorest(k = 10, nboot = 25, strat = FALSE, random = TRUE, 
                 predictions = FALSE, getmodels=FALSE)

Arguments

k integer, specify $k$ for $k$-fold cross-validation.
nboot integer, number of bootstrap replications.
strat logical, if TRUE, cross-validation is performed using stratified sampling (for classification problems).
random logical, if TRUE, cross-validation is performed using a random ordering of the data.
predictions logical, indicates whether the prediction for each observation should be returned or not (classification and regression only).
getmodels logical, indicates a list of all models should be returned. For cross-validation only.

Value

A list with the same components as arguments.


[Package Contents]