Yanjun Bao wrote
> We have say, by one id, four observations under a variable. We want STATA
> to randomly pick one observation each time it is asked. We want to use the
> randomly picked observation for each id in regression.
You can sort by a random variable within each person and than pick the first
observation or each person. If "id" is the identifier for observation the
following should do it:
.. set seed 731 /* Change seed to whatever you want */
.. gen r = uniform()
.. by id (r), sort: gen select = _n==1
.. regress yvar xvars if select
hope this helps
uli
*
* 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/
