Statalist


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

AW: AW: st: AW: dropped interaction terms from FE model


From   P K <statistics_2009@yahoo.de>
To   statalist@hsphsun2.harvard.edu
Subject   AW: AW: st: AW: dropped interaction terms from FE model
Date   Sun, 21 Jun 2009 02:23:29 +0000 (GMT)

Hi Glenn,

thanks, I checked it with a RE model instead of a FE model and discovered that the variables are indeed dropped due to 
collinearity. 
Sorry, that was my mistake.
Thanks
Pat



----- Ursprüngliche Mail ----
Von: Glenn Goldsmith <glenn.goldsmith@gmail.com>
An: statalist@hsphsun2.harvard.edu
Gesendet: Donnerstag, den 18. Juni 2009, 09:58:56 Uhr
Betreff: RE: AW: st: AW: dropped interaction terms from FE model

<>

Strange. Are the interactions still dropped if you just use -regress-?

If so, are you absolutely *sure* there's no multicollinearity problem
(e.g. by checking using -_rmcoll- or -_rmdcoll-)?

Glenn.

P K <statistics_2009@yahoo.de> wrote:

Thanks, Martin.

I checked this and there is enough variation in the dropped variables.

Also, STATA removes them when I try to estimate a RE model (instead of
a FE model).

Any other ideas on why they get dropped?

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/



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