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 on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: cox regression - half siblings


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: cox regression - half siblings
Date   Wed, 25 Aug 2010 12:05:23 +0000 (GMT)

--- On Wed, 25/8/10, Grethe Søndergaard wrote:
> I have a dataset that contains information on a population
> born in 1980-1990. Some of the persons in this dataset are
> siblings (both half siblings and full siblings). I want to
> perform cox regression on the entire population as well as
> on populations of siblings,
> i.e:
> - a population of individuals who are full siblings
> - a population of individuals who are half siblings (same
> mother,
> different fathers)
> - a population of individuals who are half siblings (same
> father,
> different mothers)

What about the population who have no siblings, the families
with one child...

> The dataset includes the following variables:
> Person_ID
> Mother_ID
> Father_ID
> Health indicators
> Education
> 
> I am going to use stcox to analyse my data. When I do the
> analyses based on siblings, I use "strata" in order to
> stratify the analysis on siblings. When doing the analyses
> for full siblings I write:
> 
> stcox i.education, strata (mother_ID father_ID)
> 
> But what do I do, when performing the analyses on e.g. half
> siblings
> with the same mother but different fathers? If I only
> stratify on mother_ID I will include all children with the
> same mother, meaning both full siblings and half siblings
> (with the same mother). So how is it possible to perform
> this analysis on half siblings only?

Say a family has three kids, two from the same mother and 
father and a third from another father, how do you define
which child should appear in which dataset? You could add
child 1 and 2 to the full sibling dataset and to the half
sibling dataset (as they are half-siblings of child 3).
That does not seem like a good solution, as now you are 
using the same observation multiple times. 

The way to solve this depends on the question and the 
theory and the data. So it can only be solved by the 
researcher.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------



      

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


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