Model-Based Boosting

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. Models and algorithms are described in \doi{10.1214/07-STS242}, a hands-on tutorial is available from \doi{10.1007/s00180-012-0382-5}. The package allows user-specified loss functions and base-learners.

mboost

mboost implements boosting algorithms for fitting generalized linear, additive and interaction models to potentially high-dimensional data.

For installation instructions see below.

Instructions on how to use mboost can be found in various places:

• Have a look at the tutorials:
  • mboost tutorial
  • mboost 2.0
• Visit the project homepage and see further tutorials and references there.

Issues & Feature Requests

For issues, bugs, feature requests etc. please use the GitHub Issues.

Installation Instructions

• Current version (from CRAN):

  install.packages("mboost")

• Latest patch version (patched version of CRAN package; under development) from GitHub:

  library("devtools")
  install_github("boost-R/mboost")
  library("mboost")

• Latest development version (version with new features; under development) from GitHub:

  library("devtools")
  install_github("boost-R/mboost", ref = "devel")
  library("mboost")

  To be able to use the install_github() command, one needs to install devtools first:

  install.packages("devtools")