Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Airey, David C" <david.airey@vanderbilt.edu> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | re: st: Merge/Joinby Question |
Date | Wed, 6 Jul 2011 14:25:19 -0500 |
. I just spent a few days manipulating data with merges and appends etc. and I can't follow your question in enough detail to think of a solution. I may just not be getting it. Sometimes showing a mock data set or subsets of your data help to spark a clear solution. > Hi - > > I have data from a propensity score match that has duplicate ids in it (data set A), > because it was with replacement. However, now I am interested in merging > data set A with an unbalanced panel data set (data set B). So, neither data set has > a unique identifier. > > Is joinby the correct command to ensure that each person (duplicated ids are > assumed to be "different" people in my post-match world) has the correct number > of observations? > > One way I considered doing this was going wide with dataset B (making id unique) > and merging (1:m) with dataset A, but this is annoyingly cumbersome with a lot of > time periods and numerous variables of interest. > > Any help would be most appreciated! > > Thanks, > Ben * * 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/