| Release 11 New Features |
Statistics Toolbox 2.2
The Statistics Toolbox 2.2 supports functions that enable you to perform cluster analysis on a dataset. Cluster analysis, also called segmentation analysis or taxonomy analysis, is a way to partition a set of objects into groups, or clusters, in such a way that the profiles of objects in the same cluster are very similar and the profiles of objects in different clusters are distinct. Cluster analysis can be performed on many different types of datasets. For example, a dataset might contain a number of observations of subjects in a study where each observation contains a set of variables. The new cluster analysis functions are summarized below.Cluster Analysis Functions
| Function |
Description |
|
Create clusters from the output of the linkage function |
|
Create clusters from a dataset |
|
Check the validity of the clusters formed by the linkage function |
|
Display the hierarchical cluster tree created by the linkage function as a dendrogram plot |
|
Get information about the relative difference between a particular link in the cluster tree and the links immediately below it |
|
Group objects in a dataset into binary clusters, based on the distance information generated by the pdist function. The linkage function links objects together using the Single linkage, Complete linkage, Average linkage, Centroid linkage, or Ward linkage algorithms.
|
|
Calculate the distance between pairs of objects in a dataset, using the Euclid, Standardized Euclid, Minkowski, Mahalanobis, or City Block metrics |
|
Normalize data. Used before calculating the pair-wise distance between objects in the dataset |