Cluster K-Meansoverview how to example data see also
Cluster K-MeansStat > Multivariate > Cluster K-Means
Use K-means clustering of observations, like clustering of observations, to classify observations into groups when the groups are initially unknown. This procedure uses non-hierarchical clustering of observations according to MacQueen's algorithm [6]. K-means clustering works best when sufficient information is available to make good starting cluster designations.
Variables: Enter the columns containing measurement data on which to perform the K-means non-hierarchical clustering of observations.
Specify Partition by: Allows you to specify the initial partition for the K-means algorithm.
Number of clusters: Choose to specify the number of clusters to form. If you enter the number 5, for example, Minitab uses the first 5 observations as initial cluster centroids. Each observation is assigned to the cluster whose centroid it is closest to. Minitab recalculates the cluster centroids each time a cluster gains or loses an observation.
Initial partition column: Choose to specify a column containing cluster membership to begin the partition process.
Standardize variables: Check to convert all variables to a common scale by subtracting the means and dividing by the standard deviation before the distance matrix is calculated. This is a good idea if the variables are in different units and you wish to minimize the effect of scale differences. If you standardize, cluster centroids and distance measures are in standardized variable space before the distance matrix is calculated.