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 on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: xtreg, fe and xtlogit, fe


From   Nick Sanders <sandersn@stanford.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: xtreg, fe and xtlogit, fe
Date   Thu, 13 Oct 2011 09:31:46 -0700

Hello Natasha,

Different models (e.g. OLS vs. nonlinear models) can get different results, and I can't claim a deep understanding about how xtlogit works, but part of the difference could be driven by something as simple as your standard error specification. In the xtreg model, your standard errors are "robust", which for xtreg translates to clustered standard errors (if I remember correctly). As the xtlogit specification isn't doing any standard error correction.

Best,
Nick

On Oct 13, 2011, at 7:04 AM, natasha agarwal wrote:

> Dear Everyone,
> 
> I was trying to estimate the following model
> 
> xtreg x  a y y*g, fe vce(robust)
> xtlogit x a y y*g, fe
> 
> I get that the both y and the interaction term is insignificant in the
> xtreg, fe model while y is significant and the interaction term is
> insignificant in the xtlogit, fe model.
> 
> I fail to understand the discrepancy I observe in the results.
> 
> Can anyone help with this?
> 
> Thanks,
> Natasaha
> *
> *   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/


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