Re: st: Egen for logit regression

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Wed, 7/4/10, muhammed abdul khalid wrote:
> How do i test the effect on ethnicity IF all observations
> doesn't have inheritances wealth? Do i introduce another
> dummy say ''inheritance'', of which it equal to wealth>0
> at age 20? Or use egen command to create mean value of
> wealth as a proxy of starting point?

You would need to define what you mean exactly with
inheritance, in particular does it include transfers from
living parents to their kids (e.g. to start a business)
or are you using a more conventional definition which would
require that (often both) parents died.  If you use the 
latter definition then your first solution would seem wrong:
fortunately it is very common that the parents are still
alive when the kids become 20.  If you use the former 
definition, then I would consider these intergenerational
transfers as an intervening mechanism: they partly explain 
why race influences wealth. In this case I would _not_ want
to control for these transfers when estimating the effect
of race. If we would control for these transfers, we would
take away the part of the effect that we are pretty sure 
really exists (because we know and understand the mechanism)
and are left with variation we can't explain. Anyhow, this is
all academic since you appear to have no information on
intergenerational transfers in your data. 

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/