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

Re: st: Quadratic IV?

From   Austin Nichols <>
Subject   Re: st: Quadratic IV?
Date   Fri, 4 Sep 2009 10:10:45 -0400

Christian Weiß<>:
This is a FAQ on the list, answered many times e.g.
i.e. you may say
"i doubt that ivregre a b ( c c² = x y) is a viable solution"
but it is, modulo incorrect syntax.  You can also:
g c2=c^2
g xy=x*y
g x2=x^2
g y2=x^2
ivregress liml a b (c c2=x y xy x2 y2)
estat overid
estat firststage

On Thu, Sep 3, 2009 at 9:06 PM, Christian Weiß<> wrote:
> Dear Statalisters,
> I'd like to estimate the following regression modell:
> Dep. Var: a
> Indep. Vars: b c c²
> c i supposed to be instrumented by the instruments x y. If it was not
> for the additional quadratic instrument, the solution should be easy:
> ivreg(2) a b ( c = x y) - but how to include the quadratic instrument?
> i doubt that ivregre a b ( c c² = x y) is a viable solution.
> Unforuntately  the ivreg a b (c = x y) (c = x y)² syntax is not allowed.
> Do you have any suggestions for me how to solve this problem?
> Best regards
> Chris

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index