# Re: st: genealogy: how to calculate sibship size

 From n j cox To statalist@hsphsun2.harvard.edu Subject Re: st: genealogy: how to calculate sibship size Date Thu, 07 Sep 2006 10:54:26 +0100

Ronnie Babigumira already directed you to an FAQ explaining various tricks. It may be more complicated than you need.

I just wanted to add that if each observation is a person and your variables are as stated then the number of people sharing each pair of parents is given directly by

bysort ??ther_id : gen n = _N

Thus suppose that our data are

donor_id father_id mother_id
1 A Z
2 A Z
3 A Y
4 A Y
5 B Y
6 C X

then after this

bysort ??ther_id : gen n = _N

you have

donor_id father_id mother_id
1 A Z 2
2 A Z 2
3 A Y 2
4 A Y 2
5 B Y 1
6 C X 1

Note that you don't need a combined id, as you can just
use the two parent ids jointly.

(I enjoyed using the wildcard ??ther_id, as this will catch

father_id mother_id

and (almost certainly) nothing else in your data. If you are
really using French then fortuitously (and fortunately)

??re_id

works the same way.)

Nick
n.j.cox@durham.ac.uk

BAIJER Jan 212040, Ph.D.

I'm trying to have Stata calculate the number of sibs for each of the
families in a list that is composed as follows :

donor_id
father_id
mother_id

From this, I can calculate a unique identifier for the parent couple, by
concatenation of father_id and mother_id.

But, I have no idea how to proceed for this one ...

*
* 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/