Dear Statlisters,
I have a standard person-by-variable dataset and would like to create a
person-by-person similarity matrix. The data are multiple-choice type
format (a nominal variable with 4 categories). I'd like to compute the
similarity matrix using a simple matching measure, where the coefficient
would be the proportion of times that two people agree exactly.
As I understand it, the simple matching coefficient available in Stata
assumes that the data are binary: [MV] measure_option says "Stata treats
nonzero values as one when a binary value is expected" (p. 362).
Is there a built-in function for calculating a more general matching
coefficient for nominal data? If not, has anyone else programmed it?
Thanks for your time.
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
[email protected]
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/
