Stopping rules in cluster analysis on binary data

[Malene Christensen]

Hi everyone.
I have conducted an average linkage, hierarchical cluster analysis using a simple matching coefficients as all my variables are binary (present=1, absent=0). Now I have found that the stopping rules in cluster analysis supported by Stata are the Calinski–Harabasz pseudo-F and the The Duda–Hart Je(2)/Je(1) index both for continous data. Is there any way I could for instance use an adaptation of the Goodman ad Kruskal's gamma statistic for categorical data or something else like it in Stata?

I have 217 observations in my dataset, and they are weakly clustered.

I hope you can help

[Dave Airey]

Stata (14) does allow you to add your own stopping rule if that is your question. Help says to see the cluster programming subroutines section and an illustration is provided how to do this. Are you asking if someone has implemented what you want?

[Malene Christensen]

Yes. I am looking for someone who already did this, as the cluster programming subroutines are a bit over my Stata skill-level. Otherwise, maybe someone is aware of an existing userwritten programme that can help me?