Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: cross grouping a family w siblings and stepsiblings


From   "Sarah Edgington" <sedging@ucla.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: cross grouping a family w siblings and stepsiblings
Date   Mon, 2 May 2011 12:34:23 -0700

.
This is the sort of complicated problem that requires that you work out the
conceptual pieces really clearly before you start working on the programming
part.  You'll need to think very carefully about what information you have
and what information you can generate from that.
You have a mother ID and father ID for each child, right?  Are those the IDs
of the biological parents or something else?  If those IDs identify
biological parents what are you using to determine how households are
currently constituted?  Is all your data from a single point in time?  If
not, you're going to have to take into account the fact that as family
compositions change who the stepsiblings are will also change.

I think you'll need to create two family IDs to take into account the fact
that children cannot be uniquely classified into a single family.  Do you
have something like a partner ID for mothers and fathers?  If so, you could
create a first family ID that is created by combining the mother's ID with
the mother's partner ID.  Then create a second family ID that is created
from the father's  partner's ID and the father's ID (assuming father ID is
biological father; if it's not biological father ID I'm not actually sure
you have enough info to proceed).  For children living in a household with
both biological parents you would only create the first family ID.  The
reason you want to create the second family ID with the father's partner's
ID first and then the father's ID is that by putting the IDs in the same
order (and how you combine them really depends on the exact form of the
existing IDs) you will be able to match children whose second family ID
matches other children's first family ID.  To generate counts of children
within families you could create a file with duplicate records for children
in two families.  Then create a unique family ID that is the first family in
the first record for that child and the second family for the second record.
Kids in only one family will have only one record and one unique family ID.


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index