st: working with similarity matrices

["Clarence C. Gravlee" <cgravlee@fsu.edu>]

Statalisters,

I have a standard case-by-variable profile matrix like this

  A B C D E F
1
2
3
4


and want to compute a case-by-case similarity matrix like this

  1 2 3 4
1
2
3
4

In this instance, I want to use Jaccard's coefficient of similarity, 
though at other times I'll want to use another similarity measure.  I 
need to be able to save this similarity matrix so that I can work with 
it using multidimensional scaling, principal components analysis, etc. 
Is this sort of thing possible in Stata?

It appears that several people have asked related questions about 
working with similarity matrices in the last couple of years, and no one 
seems to have gotten very far.  See, for example

http://www.stata.com/statalist/archive/2004-07/msg00605.html
http://www.stata.com/statalist/archive/2005-02/msg00040.html

Is part of the issue that Stata assumes users would want to work with 
similarities only as part of cluster analysis?

As is probably apparent from my question, I don't have any programming 
experience in Stata.  I'm willing to learn, but given my needs, I wonder 
if Stata is the best language to invest in learning, or whether I ought 
to look elsewhere (like R).  I'd welcome your suggestions.

Thanks for your sharing your time and expertise.

Lance Gravlee
--
Clarence C. Gravlee, Ph.D.
Assistant Professor
Department of Anthropology
Florida State University
Tallahassee, FL 32306-7772
(850) 644-4754
(850) 645-0032 FAX
cgravlee@fsu.edu
http://lance.qualquant.net/

Research Associate
Center for Demography and Population Health



*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/