Maximum likelihood regression trees

    Authors

    X. G. Su; M. Wang;J. J. Fan

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    J. Comput. Graph. Stat.

    Keywords

    CART; information criteria; pruning trees; tree size selection; MODEL SELECTION; SURVIVAL TREES; DECISION TREES; Statistics & Probability

    Abstract

    We propose a method of constructing regression trees within the framework of maximum likelihood. It inherits the backward fitting idea of classification and regression trees (CART) but has more rigorous justification. Simulation studies show that it provides more accurate tree model selection compared to CART. The analysis of a baseball dataset is given as an illustration.

    Journal Title

    Journal of Computational and Graphical Statistics

    Volume

    13

    Issue/Number

    3

    Publication Date

    1-1-2004

    Document Type

    Article

    Language

    English

    First Page

    586

    Last Page

    598

    WOS Identifier

    WOS:000223292000004

    ISSN

    1061-8600

    Share

    COinS