Dear all,
we have a study in which case farms were identified, then control farms were
matched to them on region and herd size (one control per case), and finally
between 5 and 13 cows per farm (depending on farm size) were randomly
enroled in the study.
In order to evaluate the association between several cow and herd level
variables and a binary (0/1) outcome variable, a logistic regression model
seems suitable. However, both the matching at farm level and the cluster
effect of several cows per farm in the study need to be considered in the
analysis.
I am looking for some recommendations on how to tackle this analysis problem
in STATA.
Thanks for your advice - Regards Marcus
___________________________________________
PD Dr. Marcus Doherr, Ph.D.
Dipl. ECVPH, FTA Epidemiologie
NeuroCenter & Abteilung Klinische Forschung
* Dept. Klinische Veterin�rmedizin, Universit�t Bern
Bremgartenstrasse 109A, Postfach, CH - 3001 Bern
* +41.31.631.2428 FAX ...2538
* [email protected]
www.neurocenter-bern.ch
*
* 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/