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: How to get -margins- give predicted probabilities faster?


From   Friedrich Huebler <fhuebler@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: How to get -margins- give predicted probabilities faster?
Date   Mon, 19 Jul 2010 18:03:03 -0400

Duha,

If you don't need standard errors you can speed up -margins- with the
-nose- option.

. margins, at((mean) _all x1=(0 1) x2=(0 1) x3=(10(1)20)) post nose

Friedrich

On Mon, Jul 19, 2010 at 11:47 AM, Duha Altindag <daltin2@tigers.lsu.edu> wrote:
> Greetings,
> I wonder if -margins- can be made work faster.
>
> Say I have two indicators (x1 and x2) and two continuous variables (x3
> x4). The following piece takes a while with Stata SE and a recently
> purchased computer (fairly fast).
>
> probit y x1#x2 x3 x4
> margins, at((mean) _all x1=(0 1) x2=(0 1) x3=(10(1)20)) post
>
> But instead if created dummies associated with x1#x2 and run -probit-
> and calculate predicted probabilities with -nlcom- at the above
> specified values, I'd be done faster.
>
> Is there a way to get -margins- to do this job faster?
> If not, do I gain something by using -margins- over the second way
> described above?
*
*   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