Statistics Toolbox

manovacluster

Plot dendrogram showing group mean clusters after MANOVA

Syntax

• manovacluster(stats)
  manovacluster(stats,'method')
  H = manovacluster(stats)
  

Description

manovacluster(stats) generates a dendrogram plot of the group means after a multivariate analysis of variance (MANOVA). stats is the output stats structure from manova1. The clusters are computed by applying the single linkage method to the matrix of Mahalanobis distances between group means.

See dendrogram for more information on the graphical output from this function. The dendrogram is most useful when the number of groups is large.

manovacluster(stats,'method') uses the specified method in place of single linkage. 'method' can be any of the following character strings that identify ways to create the cluster hierarchy. See linkage for further explanation.

'single'	Shortest distance (default)
'complete'	Largest distance
'average'	Average distance
'centroid'	Centroid distance
'ward'	Incremental sum of squares

H = manovacluster(stats,'method') returns a vector of handles to the lines in the figure.

Example

Let's analyze the larger car dataset to determine which countries produce cars with the most similar characteristics.

• load carbig
  X = [MPG Acceleration Weight Displacement];
  [d,p,stats] = manova1(X,Origin);
  manovacluster(stats)
  
  
  

See Also
cluster, dendrogram, linkage, manova1

manova1

mean