Fulltext

Model-based boosting in high dimensions

Hothorn, Torsten ; Bühlmann, Peter

In: Bioinformatics, 2006, vol. 22, no. 22, p. 2828-2829

Ajouter à la liste personnelle
    Titre
    • Model-based boosting in high dimensions
    Auteur
    • Hothorn, Torsten. Institut für Medizininformatik, Biometrie und Epidemiologie, Friedrich-Alexander-Universität Erlangen-Nürnberg Waldstraße 6, D-91054 Erlangen, Germany
    • Bühlmann, Peter. Seminar für Statistik, ETH Zürich CH-8092 Zürich, Switzerland
    Type de document
    • Postprint
    Identifiant OAI-PMH
    • oai:doc.rero.ch:302678
    Summary
    Summary: The R add-on package mboost implements functional gradient descent algorithms (boosting) for optimizing general loss functions utilizing componentwise least squares, either of parametric linear form or smoothing splines, or regression trees as base learners for fitting generalized linear, additive and interaction models to potentially high-dimensional data. Availability: Package mboost is available from the Comprehensive R Archive Network () under the terms of the General Public Licence (GPL). Contact: Torsten.Hothorn@R-project.org