One answer to this is to recast your problem
as an -anova- problem. Then you have one continuous
and one categorical predictor.
anova y x1 x2, continuous(x1)
Nick
[email protected]
Hui Wang
> When we use xi command in regression, say "xi: reg y x1
> i.x2", and suppose
> that the discrete variable x2 takes 10 possible value. After
> the regression,
> what is the command to test the joint significance of the x2 dummies
> generated by stata?
>
> I've tried the following:
>
> xi: reg y x1 x2
>
> xi: test i.x2;
> test _Ix2_*;
> test _Ix2_1-_Ix2_9;
>
> Neither of them works. (I really do not want to enter
> something like: test
> _Ix2_1 _Ix2_2 ... _Ix2_9.)
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/