Hi All,
I have a proximity matrix data file, which I saved out from a Hierarchical Cluster Analysis (method = Ward, measure = Squared Euclidean Distance). The matrix has 83 cases (var1
to var83), and 4 grouping variables (cluster2 to cluster5) that identify case membership to 2, 3, 4, or 5 cluster solutions. I would like (a) to calculate the average of all distances
between cases within each cluster for the different cluster solutions (2 to 5), (b) to calculate each cluster centroid, and (c) to print them in the output file. Could anyone suggest
the correct syntax to accomplish this goal? I have been thinking about the LOOP command and conditional statements, but this task is beyond my beginner knowledge. I would
greatly appreciate any help. Thank you.
Best,
Frank
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
