Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: RE: HAC SE in high dimensional regression
From
Diana Salvia <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: RE: HAC SE in high dimensional regression
Date
Sun, 5 Jun 2011 12:52:22 -0700 (PDT)
Thank you Eric. I actually was not clear enough (and made an error) when posting my question. Some of my independent variables are actually not dummies but take on values eg 1, 2, 3,�4, and others that are dummies represent several ways fixed effects.
My goal is to compute newey-west on a small subset (5) of all 8,000 independent variables.
Any suggestion?
Thanks again.
----- Original Message -----
From: DE SOUZA Eric <[email protected]>
To: "[email protected]" <[email protected]>
Cc:
Sent: Sunday, June 5, 2011 12:15 PM
Subject: st: RE: HAC SE in high dimensional regression
-areg- is what you need. Type -help areg-
Put all your dummy variables in the option -absorb- , and use the option -vce- for SE corrections
Eric de Souza
College of Europe
Brugge (Bruges), Belgium
http://www.coleurope.eu
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Diana Salvia
Sent: 05 June 2011 18:18
To: [email protected]
Subject: st: HAC SE in high dimensional regression
Hi
I am trying to run a regression with a large number of independent variables (approximately 8,000 dummies) and would like to compute SE corrected for heteroskedasticity and serial correlation. However, I only need corrected SE for five of my independent variables (I am not interested on the SE of the dummies). Using the command newey is not an option because it will literally take years to run (I only need SE for five and not for all of my independent variables).
I would really appreciate your help!
thanks
*
* 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/
*
* 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/
*
* 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/