Cluster Analysis - Quick tab

Select the Quick tab of the Cluster Analysis dialog box to access the options described here.

Algorithm

Choose either the k-Means, EM, or Tree Clustering algorithm. Refer to the Introductory Overview for a discussion of these methods.

Number of clusters

Specify the Number of clusters; you can also determine the number of clusters automatically from the data by using any of the cross-validation methods available on the Validation tab (see also the section on v-fold cross-validation in the Introductory Overview for details). If either v-fold cross-validation is requested or a Test sample variable and code is specified on the Validation tab, this option is not available (it will be dimmed since the number of clusters are determined automatically from the data). This option is not available when Tree Clustering is selected as the Algorithm.

Number of iterations

Specify the maximum number of iterations to be performed during the clustering. The default value, 50, is usually sufficient even for large data sets and many clusters. This option is not available when Tree Clustering is selected as the Algorithm.