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 at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: sign of coefficients in a xtprobit


From   David Hoaglin <dchoaglin@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: sign of coefficients in a xtprobit
Date   Sat, 9 Feb 2013 10:29:06 -0500

Hi, Luke.

You did not give us the -xtprobit- command that you used.  If the
regression involves other predictors besides that dummy variable, it
may not be surprising that the coefficient of the dummy variable does
not have the sign that you expect.  That coefficient should be
interpreted as the effect of the dummy variable after adjusting for
simultaneous linear change in the other predictors in your model.

David Hoaglin

On Sat, Feb 9, 2013 at 4:38 AM, Luca Marcolin <gonzalo07@hotmail.it> wrote:
> Hello,
> I am currently dealing with a xtprobit regression.
> I
> have experimented a problem with the coefficient of a dummy variable. IT
>  has not the sign that I expect, that is logical and obvious.
> Maybe
> there is a problem in my dataset, when I have put in the data, or is a
> specific - and curious - characteristic of my sample, but maybe is a
> "technical" problem.
> Can you suggest me some commands or procedures to understand if the variable is bad-built or there are some technical problems?
>
> Thanks
>
> Luke
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


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