Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "sdm1" <sdm1@york.ac.uk> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | st: RE: RE: how to -expand- and attach new group id to panel data |
Date | Fri, 1 Oct 2010 11:19:00 +0100 |
Thanks Nick. I want to use -xtivreg, re- but to give more weight to some groups. As there is no weight facility with -xtivreg, re- I thought of -expand-ing the groups in lieu of weighting, and then running -xtivreg, re-. I appreciate that the standard errors will be meaningless but it is the coefficients that I am most interested in. Steve -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Nick Cox Sent: 30 September 2010 17:58 To: 'statalist@hsphsun2.harvard.edu' Subject: st: RE: how to -expand- and attach new group id to panel data Two answers: 1. Why and how are you discriminating between clones of any panel? 2. -egen, seq()-. Nick n.j.cox@durham.ac.uk Steve I have a balanced panel data set with 3 annual observations for each of 3 groups e.g., Group_id year 1 78 1 79 1 80 2 78 2 79 2 80 3 78 3 79 3 80 Suppose I use -expand- to generate, say, one extra copy of the data for group_id 2 and two extra copies of the data for group_id 3. Now I have: Group_id year 1 78 1 79 1 80 2 78 2 79 2 80 3 78 3 79 3 80 2 78 2 79 2 80 3 78 3 79 3 80 3 78 3 79 3 80 How do I give new group_ids to the copied data so that now: Group_id year Newgroup_id 1 78 1 1 79 1 1 80 1 2 78 2 2 79 2 2 80 2 3 78 3 3 79 3 3 80 3 2 78 4 2 79 4 2 80 4 3 78 5 3 79 5 3 80 5 3 78 6 3 79 6 3 80 6 * * 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/