Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Estout and predicted signs - new questions


From   "Jann, Ben" <ben.jann@soz.gess.ethz.ch>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Estout and predicted signs - new questions
Date   Fri, 4 Mar 2005 08:42:21 +0100

Hervé wrote:
> I refer to a problem I mentioned earlier and which was solved
> by the second solution you proposed originally (the one with
> the program prsign, eclass): in my estout output, I want to
> have the results of two regressions:
>
> regress y var1 var2
> regress y var1 var2 var3.
>
> In the predicted signs column, I need to have the three
> variables var1, var2 and var3, although >the first model only
> uses var1 and var2.
>
> It seems to me that your latest solution (with tempname b) is
> related to only one model.

No, not necessarily. Consider:

  sysuse auto
  regress price mpg weight
  est sto model0
  regress price mpg weight foreign
  estimates store model1
  tempname b
  matrix `b' = e(b)
  matrix `b'[1,1] = -999   //neg. sign for mpg
  matrix `b'[1,2] = +999   //pos. sign for weight
  matrix `b'[1,3] = .z     //no sign for foreign
  matrix `b'[1,4] = 998    //? for _cons
  eret2 matrix signs = `b'
  estimates store pred
  estout pred model0 model1, cells("signs(pat(1 0 0)) b(pat(0))") ///
    substitute(-999 - 999 + 998 ?)

ben

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index