Statalist


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

st: Intra-household correlation


From   Vincenzo Carrieri <vincenzo.carrieri@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Intra-household correlation
Date   Fri, 20 Feb 2009 10:23:33 +0100

Dear Statalisters,
I have this kind of problem: I am trying to estimate the following:

Dep var: hpoor (health status)
Indep var: age, sex, income (at individual level); social exclusion in
the area (such vandalism, bad enviroment as expression of
micro-context); socio-economic characteristic of macro area (GDP, as
expression of macro-context).

a) The problem I have is that only the head of household answer to
questions about micro-context (basically : do you think that the area
in which you live has this kind of problems..) and the data-set
automatically give the same answer to all the others household
component.


 My idea is to use a multilevel model with glamm setup and two level :
individuals nested in 1) household 2) macro-area.  Two questions:

1) Is it right use household id as first level to asses the role of
micro-context? I have not an id to identify the area.
2) Basically what I need would be correct the correlation
intra-household at level 1 and intra-macro area at level 2. Can I do
it, with the problem sub a).?

I appreciate any hint. Thanks in advance
*
*   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   |   What's new   |   Site index