Eva Rueckert
>
> I am trying to bootstrap a decomposition using the syntax outlined
> in the stata manual. I want to bootstrap the whole decomposition
> procedure which includes the running of some regressions. The
> beginning of my file looks as follows:
>
> program define jmp
> version 7.0
> if "`1'"=="?" {
> global S_1 "com1 com2 com3 com4"
> exit
> }
>
> tempname jmp
>
> global list1 "educb educc educd educe educf marr childreny
> childreno ten tensq exp expsq occupa occupb occupc occupd
> occupe occupf occupg occuph indc indd indef indg indh indi indj
> indk indl indm indn indo Harjumaa West Sothcntl Nrthcntl South
> ethnic"
> local year "94 99"
> foreach yr of local year {
> reg lnwge $list1 if year==`yr' & gender==1
> gen fesample_`yr'=e(sample)==1
> /*and so on*/
>
> post `1' `topost'
> end
>
> the file does not run and the return message is:
>
> use "P:\panel.dta", clear
> . set seed 10001
> . bstrap jmp, reps(1)
> (obs=19210)
>
> too many variables specified
> r(103);
>
> now my question: does the r(103) refer to the variables I have
> specified in my global list1? And if so, is there something
> i can do
> to extend the number of variables?
>
This is a bit difficult to debug in the absence
of part of the program. You could
. set trace on
and see where it all blows up.
Nick
[email protected]
*
* 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/
