17.7.3.5 Interpreting Results of K-Means Cluster Analysis

K-Means Report Sheet

Initial Cluster Center

The first step in k-means clustering is to find the cluster centers. Run hierarchical cluster analysis with a small sample size to obtain a reasonable initial cluster center. Alternatively, you can specify a number of clusters and then let Origin automatically select a well-separated value as the initial cluster center. Note that automatic detection is sensitive to outliers, so be sure to screen data for outliers before analyzing.

Final Cluster Center

The Final Cluster Center table provides the final cluster center values.

Cluster Summary

The Cluster Summary table provides statistics on each cluster.

Distance Between Final Cluster Centers

Cluster results are good when all non-zero numbers are relatively large.

ANOVA

From the ANOVA table we can learn whether all variables should be introduced in cluster analysis. If the p-value for all four variables is larger than 0.05, we should consider excluding them from the analysis.

K-Means Cluster Membership and Distance

See the Membership column for information on how observations are clustered. Use the Distance column to see how far or close the observation is from the cluster center of its group.

Note: Observations with large distances may be outliers. Such data should be carefully examined and removed as necessary.