Re: st: saving regress results and variable names i.var#i.var

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

--- On Mon, 4/10/10, Benhoen2 wrote:
> The more frustrating problem though is how to have the
> factors in the interaction variables identified.  The 
> results seem to discard to factor names. The variable
> blkgrp (FYI "census blockgroup") has ~1,200 unique
> values in the sample (e.g., 89556, 42663, 48335), and the
> variable pv ("photo voltaic") has two values (e.g., 1=yes,
> 0=no) and to be useful the results need to be matched
> with their identifiers.  The output seems to discard these
> names and instead uses a simple integer series (blkgrp pv:
> e.g., 1 1, 1 0, 2 1, 2 0,...1199 1, 1199 0, 1200 1, 1200
> 0).  

This is why you should use post-estimation commands like 
-predict- or -predictnl-. I am sure you could figure out
the logic behind these factor variables, and I am sure 
there is a logic, but the likelihood of making an error 
is just too big. Moreover, the code would be very 
difficult to debug. So I recommend that you try to 
rethink what you want to do in terms of -predict- and/or 
-predictnl- and/or -margins-. You don't say what you want 
to do with those estimates, but with a bit of creative 
thinking you can do about anything with these commands.

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/