You can save results from your analysis to the worksheet so that you can use them in other analyses, graphs, and macros. Minitab stores the selected results in the column that you enter. For more details on any of these results, go to Interpret all statistics and graphs for Cluster K-Means.
- Cluster membership column
- Enter a column to store the final cluster membership for each observation. This column can then be used as a categorical variable in other Minitab analyses, such as discriminant analysis.
If you do not enter a storage column, the results will show the total number of observations in each cluster, but will not indicate the cluster to which each observation belongs.
- Distance between observations and cluster centroids
- Enter columns to store the distance between each observation and each cluster centroid. The number of columns specified must equal the number of clusters specified for the initial partition. Minitab stores the distances as Euclidean distances. These values can help you evaluate the within-cluster variation. For example, you can identify observations, such as extreme outliers, that are most like or most different than the average observation of each cluster.