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]
st: RE: Quantile regression with fixed effects and first differences
From
"Jacobs, David" <[email protected]>
To
"'[email protected]'" <[email protected]>
Subject
st: RE: Quantile regression with fixed effects and first differences
Date
Mon, 9 May 2011 13:10:26 +0000
In the chapter that deals with quantile regression, Wooldridge claims that (much like nonlinear estimators such as logit) one can't get decent estimates by throwing in case dummy variables to obtain fixed effects in quantile regressions. Check out the latest edition of Wooldridge, Jeffrey M. Econometric Analysis of Cross Section and Panel Data. MIT Press (I think the publication date is 2010).
Dave Jacobs
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Nick K
Sent: Monday, May 09, 2011 6:17 AM
To: [email protected]
Subject: st: Quantile regression with fixed effects and first differences
Hi,
I've been battling with this issue for ages and can't seem to get it to work.
I need to do a median regression with both time and individual fixed
effects, and the dependent variable is in first differences.
I've tried using xi:qreg .... i.year, etc., but the individual fixed
effects would give me > 25,000 dummies which Stata/my PC can't handle.
I think I've solved the first difference issue by manually doing it:
gen fDepVar = d.DepVar, but the fixed effects are killing me!
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/