Re: st: question about mlogit.

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

--- On Sat, 27/3/10, Jessica Bishop-Royse wrote:
> How would you determine whether or not to leave it as is or
> try use another model?

I said previously that you need to determine whether a 
variable is an intervening or a confounding variable. This means
that you need to formulate a theory of how you believe that all 
your variables are causally related. Based on that theory you 
can determine which variables are confounders and which 
intervening variables. You include the confounders in your model 
and exclude the intervening variables.

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/