We propose an objective Bayesian algorithm for searching the space of Gaussian directed acyclic graphical models when the variables are assumed to satisfy a given ordering. The approach used is based on non-local parameter priors and thus it is suitable for learning sparse graphs. The algorithm is implemented in C++ using the open-source library Armadillo.

Version: | 1.0 |

Depends: | Rcpp (≥ 0.9.13), RcppArmadillo (≥ 0.3.2.4) |

LinkingTo: | Rcpp, RcppArmadillo |

Published: | 2013-04-13 |

Author: | Davide Altomare, Guido Consonni and Luca La Rocca |

Maintainer: | Davide Altomare <davide.altomare at gmail.com> |

License: | GPL-2 | GPL-3 [expanded from: GPL (≥ 2)] |

NeedsCompilation: | yes |

In views: | gR |

CRAN checks: | FBFsearch results |

Reference manual: | FBFsearch.pdf |

Package source: | FBFsearch_1.0.tar.gz |

Windows binaries: | r-devel: FBFsearch_1.0.zip, r-release: FBFsearch_1.0.zip, r-oldrel: FBFsearch_1.0.zip |

OS X Snow Leopard binaries: | r-release: FBFsearch_1.0.tgz, r-oldrel: FBFsearch_1.0.tgz |

OS X Mavericks binaries: | r-release: FBFsearch_1.0.tgz |