Premium
WAGNER NETWORKS AND WAGNER TREES: A PRESENTATION OF METHODS FOR ESTIMATING MOST PARSIMONIOUS SOLUTIONS
Author(s) -
Jensen Richard J.
Publication year - 1981
Publication title -
taxon
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.819
H-Index - 81
eISSN - 1996-8175
pISSN - 0040-0262
DOI - 10.2307/1219939
Subject(s) - set (abstract data type) , computer science , tree (set theory) , data set , algorithm , mathematics , data mining , artificial intelligence , combinatorics , programming language
Summary The methods of Wagner network and Wagner tree construction are presented. A worked example, based on a set of hypothetical taxa, is examined in detail. Additional examples, representing real and artificial data sets, are also examined. The existence of alternative choices at several stages in the algorithms leads to solutions that may not be most parsimonious estimates. There apparently is no non‐arbitrary method for choosing between the alternatives. The examples presented illustrate that there may be multiple equally parsimonious solutions for a given data set and that neither algorithm can ensure a most parsimonious solution.