Dear STATA users:
I have the following issue:
the data consists of sibling pairs, both of them have been investigated with respect to the presence or absence of a disease (yes or no).
I have randomly assigned siblings as being the first or second (its not known who of them was investigated firstly, there is no ascertainment strategy). I have performed logistic regression analysis to assess the odds ratio of second siblings having the disease to the first siblings' affection status.
Now I would like to do a permutation based procedure to test for empirical significance.
If I do
.permute sib2 "logit sib1 sib2" e(chi2), reps(10000)
I would permute the affection status of sib2.
However, I would be interested to do permutation who of the siblings is the first and who the second.
Has anybody an idea ?
Thanks much,
Marcus
Dr. Marcus Fischer
Klinik und Poliklinik für Innere Medizin II
Universität Regensburg
Franz-Josef-Strauss Allee
93053 Regensburg
*
* 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/
