Functional gradient descent algorithm (boosting) for optimizing general risk functions utilizing component-wise (penalised) least squares estimates or regression trees as base-learners for fitting generalized linear, additive and interaction models to potentially high-dimensional data.

Maintainer: Benjamin Hofner <benjamin.hofner at pei.de>

Author(s): Torsten Hothorn*, Peter Buehlmann*, Thomas Kneib*, Matthias Schmid*, Benjamin Hofner*, Fabian Sobotka*, Fabian Scheipl*

Install package and any missing dependencies by running this line in your R console:

install.packages("mboost")

Depends R (>= 2.14.0), methods, stats, parallel, stabs(>=0.5-0)
Imports Matrix, survival, splines, lattice, nnls, quadprog, utils, graphics, grDevices, party(>=1.1-0)
Suggests TH.data, MASS, fields, BayesX, gbm, mlbench, RColorBrewer, rpart(>=4.0-3), randomForest, nnet, testthat(>=0.10.0)
Enhances
Linking to
Reverse
depends
CAM, expectreg, FDboost, gamboostLSS, globalboosttest, InvariantCausalPrediction, parboost
Reverse
imports
bujar, DIFboost, gamboostMSM, geoGAM, imputeR, SurvRank
Reverse
suggests
catdata, Daim, fscaret, HSAUR2, HSAUR3, mlr, OpenML, spikeSlabGAM, sqlscore, stabs
Reverse
enhances
Reverse
linking to

Package mboost
Materials
URL https://github.com/boost-R/mboost
Task Views MachineLearning , Survival
Version 2.7-0
Published 2016-11-23
License GPL-2
BugReports https://github.com/boost-R/mboost/issues
SystemRequirements
NeedsCompilation yes
Citation
CRAN checks mboost check results
Package source mboost_2.7-0.tar.gz