Re: st: problem of running xtlogit, fe

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Mon, 26/10/09, J. Li wrote:
> Thanks for the information you gave. I think you are
> right-- there is no within-individual variation for
> a big proportion of the sample I used. Can I ask
> though why the the note says that "multiple positive
> outcomes within groups encountered"? 

This procedure sometimes used for other purposes where
this might be a problem (if you are interested, the 
manual entry of -clogit- contains examples of that).
In your case it isn't a problem and you can safely
ignore that message.

> Also, I have encountered another notes saying "1,066
> individuals dropped due to all positive or all negative
> outcomes." when I was trying the same program with
> another sample. Is this essentially the same problem
> happening again? 

I have explained this before, fixed effects models only
use variation within a person. This is both a strength 
and a weakness. It is a strength because we are only
comparing within a person, so we are more likely to
compare like with like. It is a weakness because you
can only study subjects that change over time. Your
problem apparently cannot be studied with fixed effect
models, because there is too little variation within
persons. You basically have 3 choices: either you give
up and study something else, or you collect new/more/
better data, or you use a random effects model. 
Personally, I would prefer the latter option, but there
are purist (economists) who just don't like random
effects models, and who will insist that you choose 
one of the first two options. My advise: ignore them
if you can.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/