0
$\begingroup$

I used TwoStep clustering in order to cluster my binary data in SPSS. Now there is mentioned on IBM site, that:

"Note that the cluster features tree and the final solution may depend on the order of cases. To minimize order effects, randomly order the cases. You may want to obtain several different solutions with cases sorted in different random orders to verify the stability of a given solution. In situations where this is difficult due to extremely large file sizes, multiple runs with a sample of cases sorted in different random orders might be substituted." Link to the statement

I want to conduct a stability analysis now for the found clusters. Do someone know how to conduct a stability analysis for clusters (two step clustering used) in SPSS? For instance like the method from Blashfield Macintyre (1980)?

$\endgroup$
  • $\begingroup$ Recommend you to see stats.stackexchange.com/q/116856/3277, about using two-step on binary data. $\endgroup$ – ttnphns Dec 7 '16 at 12:20
  • $\begingroup$ To check stability, perform same cluster analysis several times on dataset with different case order. Examine the confusion frequency tables between the cluster membership solutions (see stats.stackexchange.com/a/219406/3277 as an example in the answer). If in a confusion matrix for two solutions all cells except just one cell in each row and column are empty or almost empty, the solutions are close, i.e. sign of stability is present. $\endgroup$ – ttnphns Dec 7 '16 at 12:29

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.