Daniele Gori <[email protected]>:
It's not really clear to me what you want from the question. Try
framing it in terms of a small dataset we can see, and results that
can be read easily in an email. Is this in the right vein?
webuse grunfeld, clear
tsset
loc tv "`r(timevar)'"
levelsof `tv', loc(tl)
foreach v in pred cons curi lagi {
g double `v'=.
}
foreach t of local tl {
cap reg mval inv l.inv if `tv'==`t'
qui if _rc==0 {
tempvar pt
predict double `pt'
replace pred=`pt' if e(sample)
replace cons=_b[_cons] if e(sample)
replace curi=_b[inv] if e(sample)
replace lagi=_b[L1.] if e(sample)
drop `pt'
}
}
On 10/18/07, Daniele Gori <[email protected]> wrote:
> Dear all,
>
> I have a large (but incomplete) panel database of firm level data and many variable, from 1995 to 2005. I would like to adopt the cross-section average estimation technique. My goal is to compute time-varying predicted values of the dependent variable. In particular, in my case I wish to estimate the following equation:
>
> yi = x1i + x2i + ui (1)
>
*
* 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/
