Statalist


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

Re: st: Panel Data dfbeta


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Panel Data dfbeta
Date   Mon, 14 Sep 2009 11:31:45 -0500

The regular DFBETA is an exercise in matrix algebra -- you don't
really refit the model n times to get them. You might be able to push
around some Kronecker products to derive similar quantities, although
of course you would have separate DFBETAs from fe, re or between
estimators. If your Stata programming skills are better than your
matrix algebra, you can run your -xtreg- [# panels] times, -post- the
results and construct your panel DFBETAs that way. If you do the
latter, that might be a nice paper for SJ :))

On Mon, Sep 14, 2009 at 10:32 AM, Steven Archambault
<archstevej@gmail.com> wrote:
> Hi all,
>
> I am trying to do a sensitivity analysis of panel data, and want to
> check what outliers are doing to my analysis. Is there an equivalent
> to dfbeta that can be used for this in a panel data setting?
>
> Thanks!
>
> -Steve
> *
> *   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/
>



-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   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   |   What's new   |   Site index