Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Heckprob - postestimation graphs


From   James McJoseph <james.mcjoseph@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Heckprob - postestimation graphs
Date   Wed, 1 Dec 2010 12:12:53 +0200

Thnks, Maarten. I have replicated the graph successfully with my data.
 The tricky part is that one of the variable that I allow to change,
(holdind the rest at means), has interaction. Now the interaction is
left at means. I suppose, in this setting the graph is only telling
half the story (better than nothing).  The next question is, how can I
include a command in there, to instruct stata to keep the dummy
variables at their observation value, while maintaining means for the
continous variables.
Much, thanks, James.

On Wed, Dec 1, 2010 at 11:18 AM, James McJoseph
<james.mcjoseph@gmail.com> wrote:
> Much thanks for this, Maarten.  You sure understood my needs. Quick
> confession "I am a newbie".  I did replicate this code with my data,
> it gives me a straightline. Obviously it must be plotting the mean.
> Plse make me understand this part of the code. How do I specify the
> "variable that changes". Say, loginc is the one that "changes" ( and
> it assumes its sample values). Plse help me further.
>
>  // set remaining variables at their mean
>  foreach var of varlist logptax loginc {
>       sum `var' if e(sample), meanonly
>        replace `var' = r(mean)
>  }
>

*
*   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/


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