cv_subsample: Cross-validation for mboost models

In parboost: Distributed Model-Based Boosting

Description

Internal cross-validation function for determing mstop in each mboost model.

Usage

cv_subsample(object, folds, grid = 1:mstop(object),
  cores_cv = detectCores())

Arguments

object	mboost object
folds	A matrix of folds
grid	The grid of mstop values used during cross-validation

Details

Takes an mboost object, a matrix of folds and the grid of values to be used during cross-validation. Returns the optimal mstop value. Uses mclapply for parallelization. The implementation is based on mboost{cvrisk.mboost}

Value

The optimal mstop value

Author(s)

Ronert Obst

References

Torsten Hothorn, Peter Buehlmann, Thomas Kneib, Matthias Schmid and Benjamin Hofner (2012). Model-Based Boosting. R package version 2.1-2.

parboost documentation built on May 2, 2019, 5:08 a.m.