Home > freetb4matlab > statistics > linkage.m

linkage

PURPOSE ^

% {@var{y} =} linkage (@var{x}, @var{method}, @var{metric})

SYNOPSIS ^

function dgram = linkage (d, method = 'single', distarg)

DESCRIPTION ^

% -*- texinfo -*-
% @deftypefn {Function File} {@var{y} =} linkage (@var{d})
% @deftypefnx {Function File} {@var{y} =} linkage (@var{d}, @var{method})
% @deftypefnx {Function File} @
%   {@var{y} =} linkage (@var{x}, @var{method}, @var{metric})
% @deftypefnx {Function File} @
%   {@var{y} =} linkage (@var{x}, @var{method}, @var{arglist})
%
% Produce a hierarchical clustering dendrogram
%
% @var{d} is the dissimilarity matrix relative to @var{n} observations,
% formatted as a @math{(n-1)*n/2}x1 vector as produced by @code{pdist}.
% Alternatively, @var{x} contains data formatted for input to
% @code{pdist}, @var{metric} is a metric for @code{pdist} and
% @var{arglist} is a cell array containing arguments that are passed to
% @code{pdist}.
%
% @code{linkage} starts by putting each observation into a singleton
% cluster and numbering those from 1 to @var{n}.  Then it merges two
% clusters, chosen according to @var{method}, to create a new cluster
% numbered @var{n+1}, and so on until all observations are grouped into
% a single cluster numbered @var{2*n-1}.  Row @var{m} of the
% @math{m-1}x3 output matrix relates to cluster @math{n+m}: the first
% two columns are the numbers of the two component clusters and column
% 3 contains their distance.
%
% @var{method} defines the way the distance between two clusters is
% computed and how they are recomputed when two clusters are merged:
%
% @table @samp
% @item 'single' (default)
% Distance between two clusters is the minimum distance between two
% elements belonging each to one cluster.  Produces a cluster tree
% known as minimum spanning tree.
%
% @item 'complete'
% Furthest distance between two elements belonging each to one cluster.
%
% @item 'average'
% Unweighted pair group method with averaging (UPGMA).
% The mean distance between all pair of elements each belonging to one
% cluster.
%
% @item 'weighted'
% Weighted pair group method with averaging (WPGMA).
% When two clusters A and B are joined together, the new distance to a
% cluster C is the mean between distances A-C and B-C.
%
% @item 'centroid'
% Unweighted Pair-Group Method using Centroids (UPGMC).
% Assumes Euclidean metric.  The distance between cluster centroids,
% each centroid being the center of mass of a cluster.
%
% @item 'median'
% Weighted pair-group method using centroids (WPGMC).
% Assumes Euclidean metric.  Distance between cluster centroids.  When
% two clusters are joined together, the new centroid is the midpoint
% between the joined centroids.
%
% @item 'ward'
% Ward's sum of squared deviations about the group mean (ESS).
% Also known as minimum variance or inner squared distance.
% Assumes Euclidean metric.  How much the moment of inertia of the
% merged cluster exceeds the sum of those of the individual clusters.
% @end table
%
% @strong{Reference}
% Ward, J. H. Hierarchical Grouping to Optimize an Objective Function
% J. Am. Statist. Assoc. 1963, 58, 236-244,
% @url{http://iv.slis.indiana.edu/sw/data/ward.pdf}.
% @end deftypefn
%
% @seealso{pdist,squareform}

CROSS-REFERENCE INFORMATION ^

This function calls: This function is called by:
Generated on Sat 16-May-2009 00:04:49 by m2html © 2003