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

st: RE: estout help - keeping equations and coefficients


From   "Ben Jann" <ben.jann@soz.gess.ethz.ch>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: estout help - keeping equations and coefficients
Date   Thu, 12 Jan 2006 11:24:36 +0100

Erin wrote:
> I'm using the estout command after running a mulitnomial 
> logit regression and then storing the estimates. 
...
> If I put the variable names in the keep () portion of
> the command, I only get the coefficients from the first 
> equation.

If a coefficient specified in the -keep()- option appears 
in several equations, only the first occurrence of the 
coefficient will be printed, unless the relevant equations 
are explicitly specified in -keep()-. Thus, Erin should 
type something like -keep(eq1:var eq2:var ...)-. Note that 
it may be more convenient to use the -drop()- option, which 
applies to *all* equations. Example:

    . sysuse auto
    . mlogit rep78 price weight foreign if rep78>=3
    . estout, keep(weight)
            .
            b
    4
    weight  .0004082

    . estout, keep(4:weight 5:weight)
            .
            b
    4
    weight  .0004082
    5
    weight  -.0013343

    . estout, drop(price foreign _cons)
            .
            b
    4
    weight  .0004082
    5
    weight  -.0013343

I think that it would indeed be superior if -keep()- 
automatically kept the coefficients from all equations. 
However, -estout- passes the -keep()- option to the 
internal call of official -estimates table-. Thus, 
-estimates table- would have to be fixed, not -estout-.

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