[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: reg3 is not doing what I need it to do, suggestions?
> -----Original Message-----
> From: firstname.lastname@example.org
> [mailto:email@example.com] On Behalf Of Anna G
> Sent: 16 July 2006 23:44
> To: firstname.lastname@example.org
> Subject: st: reg3 is not doing what I need it to do, suggestions?
> Dear Statalist members,
> thank you so much for your incredible help so far.
> I have a question regarding reg3.
> I am trying to estimate the following system of equations:
> z=x-hat $variables
> x=y-hat prices $variables
> y=assets $variables
> I am coding this as
> reg3 (z x $variables)
> (x y prices $variables)
> (y assets $variables)
> The results however do not seem to be giving me the
> coefficients on y-hat and x-hat but rather on y and x.
> Any suggestions? I've read thoroughly the reference on the
> command, and the discussion on reg3 in the statalist.
You're getting coefficients on y and x because that's how you've coded
it, and, more generally, that's what 3SLS estimation of a system of
equations is supposed to give you. Perhaps the "y-hat" and "x-hat" you
mention are fitted values? If so, then (just as in 2SLS) they are
temporary variables in 3SLS that are a means to an end and usually not
of any inherent interest.
Prof. Mark Schaffer
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS
tel +44-131-451-3494 / fax +44-131-451-3296
> For people interested, the following are my variables:
> z - nutritional status z-score of children in the household x
> - caloric availability at the household level y - income, hh-level
> The above are all simulataneously determined.
> variables -- hh and province-level controls.
> Thank you in advance.
> Stata 8.2 intercooled on windows xp
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
* For searches and help try: