You'd have to have to save the estimates AFTER
applying -check-. Thus, type
reg y x* w1 w2
check
est store regr1
est table regr1 , stats(N myp)
Have you seen -estadd- (ssc d estadd)? With -estadd-
you could do things such as
program define estadd_check, eclass
testparm x*
ereturn scalar myp=r(p)
end
reg y x* w1
est store regr1
reg y x* w1 w2
est store regr2
estadd *, s(check)
est table *, stats(N myp)
ben
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of E.
> Michael Foster (UNC_SPH)
> Sent: Thursday, August 25, 2005 5:08 PM
> To: [email protected]
> Subject: st: results of -testparm- in table by estimate
>
>
> Hi,
>
> I want to feed the results of -testparm- to -est-, but -testparm-
> outputs r-class not e-class (and my understanding is that -est- can
> include e() scalars)
>
> so, I tried to trick the program (famous last words)
>
> program define check , eclass
> testparm x* // the regressors in
> question start with x
> ereturn scalar myp=r(p) // an -ereturn list- shows this worked
> end
>
> reg y x* w1 w2 // and so on
> est store regr1
> est for regr1 : check
>
> est table regr1 , stats(N myp)
>
> No sign of myp in the table! just a blank row, appropriately
> labelled.
>
> Where am I screwing up?
>
> professor of maternal and child health
> university of north carolina
>
> *
> * 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/
>
*
* 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/
