<>
Look at -h tsvarlist- and use the lag operator "L." there. Although your
approach should work in priciple...
*************
clear*
set obs 100
//unbalanced!
gen x= cond(runiform()<0.1,.,rnormal())
//for by
gen dummy=_n>_N/2
bys dum: gen y=x[_n-1]
l, noo sepby(dum)
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Luis Bernardo
Torres Ruiz
Gesendet: Montag, 18. Mai 2009 22:30
An: [email protected]
Betreff: st: Aggregate and Microdata
Dear Stata Users,
Im using a microdata set. Im estimating aggregates with the data set. The
data set is unbalanced. A situation arises when I lag the variables by
sort PLANT YEAR STATE COUNTY ECOGROUP FIRM
quietly by PLANT: gen Ait1= aggregateprod[_n-1]
It generates missing values for the lag variable of the aggregate, but there
should a value(with the exception of the first year), since Ait is the
aggregate value by year. How can I change the missing values to the actual
values without doing a replace for each year. I thank you in advance for all
your help.
Sincerely,
Luis
*
* 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/
*
* 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/
