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]

st: Fixed Effects with ID specific Time Trends - Computation Time


From   Franco Solleza <solleza.f@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Fixed Effects with ID specific Time Trends - Computation Time
Date   Wed, 6 Mar 2013 10:33:17 -0500

Hi,

I am currently running a regression on panel data where the right hand
side includes fixed effects on an id variable, and a time trend for
each id variable. As you might imagine this leads to a large number of
parameters (twice the number of id variables minus 1 -- for the
dummy).

Ignoring for a moment issues that might arise concerning degrees of
freedom, the issue I am running into is when there are many id
variables.

Sometimes, the regressions have ~28k parameters.

The command I am using to run this model is:

xi: areg y x id*_time_trend [aw=weightvariable], absorb(id)

The issue I run into is that these models take more than 24 hours to run!

I've been trying to figure out a way to speed up computation time but
have not been able to do so. If anyone has any suggestions on how to
speed things up, that would be great!

Thanks!
Best,

--
fps
solleza.f@gmail.com
*
*   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