AUCRFcv {AUCRF}R Documentation

Repeated cross validation of the AUC-RF process.

Description

Performes a repeated cross validation analysis and computes the probability of selection for each variable.

Usage

  AUCRFcv(x, nCV = 5, M = 20)

Arguments

x

an object of class AUCRF.

nCV

number of folds in cross validation. By default a 5-fold cross validation is performed.

M

number of cross validation repetitions.

Details

The results of this repeated cross validation analysis are (1) a corrected estimation of the predictive accuracy of the selected variables and (2) an estimate of the probability of selection for each variable.
The AUC-RF algorithm is exhaustively described in Calle et. al.(2011).

Value

The same AUCRF object passed (see AUCRF) as argument but updated with the following components:

cvAUC

mean of AUC values in test datasets of the optimal sets of predictors.

Psel

probability of selection of each variable as the proportion of times that is selected by AUC-RF method.

References

Calle ML, Urrea V, Boulesteix A-L, Malats N (2011) "AUC-RF: A new strategy for genomic profiling with Random Forest". Human Heredity. (In press)

See Also

OptimalSet, AUCRF, randomForest.

Examples

  # Next steps take some time
  
  # load included AUCRF result example:
  # data(fit)
  
  # call AUCRFcv process:
  # fitCV <- AUCRFcv(fit)
  
  # The result of this example is included:
  
  data(fitCV)
  summary(fitCV)
  plot(fitCV)

[Package AUCRF version 1.1 Index]