<>
**********
clear*
set obs 100
//id
gen id=_n
//expand to # of time periods
expand 10
//time var
bys id: gen time=_n
compress
//unbalanced
drop if runiform()<0.1
xtset id time
xtdes
//sample 10% w/o regard to units
preserve
sample 10
restore
//sample 10% of panel units
gen x=runiform()
bys id: keep if x[1]>0.9
drop x
**********
HTH
Martin
_______________________
----- Original Message -----
From: <[email protected]>
To: <[email protected]>
Sent: Friday, July 03, 2009 6:28 PM
Subject: st: Random subset from existing panel dataset
Dear statalist,
I would like to do something that is pretty straight forward, but I do not
have the stata skills to do this and would appreciate some help.
I have an unbalanced panel data set (almost 101.000 observations) which is
too large to work with. The dataset looks like:
Id year y(dependent variable) x1 x2 x3 (many many
covariats)
1 2000
1 2001
1 2002
2 2003
2 2004
3 1998
3 1999
3 2000
3 2001
3 2002
3 2003
3 2004
3 2005
The dataset is already xtset with identifier (ID) and time (year). Because
the original dataset is too large I would like to take a random subsample
(containing of ca. 1000 observation) out of the original dataset. I have
already tried to follow the advices from the FAQ "How can I take random
samples from an existing dataset?", but it does not work for me.
Does somebody could help me to solve this problem?
Best regards
Frauke
___________________________________
Frauke Rüther, Dipl.-Kffr., M.A.
Research Associate
University of St.Gallen
Institute of Technology Management
Dufourstrasse 40a
CH - 9000 St. Gallen
Phone +41 (0)71 224 7225
Fax +41 (0)71 224 7301
Email [email protected]
Web www.item.unisg.ch
*
* 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/
