Perhaps, something like this:
webuse nlswork, clear
sort idcode year
bysort idcode: egen wave = seq()
tsset idcode wave
gen pred_wave =.
logit union age collgrad tenure hours if wave==1
predict pred if e(sample)
replace pred_wave = pred
drop pred
levelsof wave if wave >1, local(levels)
foreach i of local levels {
qui {
logit union l.ln_wage l.age l.collgrad l.tenure l.hours if wave==`i'
predict pred if wave == `i'
replace pred_wave= pred if wave == `i'
drop pred
}
}
keep pred wave idc
reshape wide pred, j(wave) i(idco)
egen predfinal = rowmax( pred*)
Scott
*
* 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/
