Workspace Node: K-Means Clustering - Results - Advanced Tab

In the K-Means Clustering node dialog box, under the Results heading, select the Advanced tab to access the following options.

Element Name Description
Descriptive statistics for each cluster Select this check box to produce spreadsheets, one for each cluster, containing the descriptive statistics.
Members of each cluster & distances Select this check box to produce the (Euclidean) distances of the objects (cases or variables, depending on the selection in the Cluster box on the Specifications Quick or Advanced tab) from their respective cluster center (mean). This enables you to identify potential "bad" cluster members, that is, objects that are very distant from the cluster center, yet apparently do not belong to any other cluster (i.e., they are even further away from the centers of alternative clusters). These distances will be displayed in standard spreadsheets, each spreadsheet showing the results for one cluster.
Distances The distance between two objects or cluster centers i and j are computed as:

Di,j = Ö{S[(xi - xj )2 /ND]}

where the summation is over the ND dimensions in the current analysis. Note that these distances are computed from raw (not scaled) data value; consequently, variables in the analyses with a large range of values may contribute disproportionately to the computed distances and, hence, the final cluster solution; see also, Differences in k-Means Algorithms in Generalized EM & k-Means Cluster Analysis vs. Cluster Analysis.

Options / C / W. See Common Options.

OK Click the OK button to accept all the specifications made in the dialog box and to close it. The analysis results will be placed in the Reporting Documents node after running (updating) the project.