>Then, if I keep running the same outreg command as above, another message
>"variable __000005 not found" or "variable __000006 not found" comes out.
>However, after several times, it worked and gave the result at reg1.out. It is
>just very annoying, and I was not able to run in do file since it would stop due
> to the messages. the more variables I included in the regression, the more
>messages I got, the more runs I have to do untile get the result.
Your Stata is randomly dropping variables, including temporary variables. The
more variables you include, the higher the chance that one of them gets dropped.
Like a binominal trial, you have to do many times to get a lucky run.
See the following linke by Alan R. for dealing with this problem.
http://www.stata.com/statalist/archive/2008-08/msg01142.html
_________________________________________________________________
See how Windows connects the people, information, and fun that are part of your life.
http://clk.atdmt.com/MRT/go/msnnkwxp1020093175mrt/direct/01/
*
* 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/
