Re: st: correlating responses within the same variable

[Nick Cox <njcoxstata@gmail.com>]

Part of this is an FAQ.

http://www.stata.com/support/faqs/data-management/listing-observations-in-group/

Nick
njcoxstata@gmail.com


On 18 March 2014 19:29, Patrick Abi Nader <p0abin01@gmail.com> wrote:

> Thank you everyone that helps out!
> I am using stata 13 and have 147 variables and 236 observations.
>
> Observations represent information collected on children. Children may
> be siblings I have 163 families.
>
> I want to see if responses of families with multiple children were
> similar for each one of those children. for example I have variable x,
> that was measured on z1, and z2 (from family 1), and on z3, z4 ( from
> family 2). I want to know if answers for each child from the same
> family were the same on x. How do you suggest I do that? I am thinking
> that I may need to create new variables but I am not sure conceptually
> how to go about that.
>
> I already created a variable tagging families by using this code
> egen tag= tag(family_id) (thanks to Nick)
>
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/