<>
Martin said
What would the test with one df look like in my example?
In my (quite similar) example:
webuse grunfeld, clear
g byte d = company<7
xi: reg invest kstock mvalue i.time i.company if d
est store zero
xi: reg invest kstock mvalue i.time i.company if !d
est store one
suest zero one
test [zero_mean]kstock+[zero_mean]mvalue=[one_mean]kstock+[one_mean]
mvalue
which is the same, conceptually, as that appearing in various postings
(in which there were three coeffs. in the sum, not two, but ça ne fait
rien).
Kit Baum
kitbaum@me.com
*
* 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/