[gov2001-l] imputing and matching - Gov2001 - lists.gking.harvard.edu

List overview All Threads
Download

[gov2001-l] imputing and matching

[gov2001-l] our title and abstract

[gov2001-l] abstract

woolfalk＠fas.harvard.edu

1 May 2007 1 May '07

3:36 p.m.

Hi, If we want to both impute and match, what is the best order for doing these procedures? There has been some disagreement about this. Is it appropriate to match on imputed data? Thanks, Miya -- K. Miya Woolfalk Graduate Student Harvard University Government and Social Policy

Reply

Show replies by date

hlk23＠cornell.edu

1 May 1 May

3:41 p.m.

Miya, I think the correct order is to first impute, then match within each imputed dataset. Otherwise you would have to deal with the NAs during the matching. Holger Miya Woolfalk wrote:

Hi, If we want to both impute and match, what is the best order for doing these procedures? There has been some disagreement about this. Is it appropriate to match on imputed data? Thanks, Miya -- K. Miya Woolfalk Graduate Student Harvard University Government and Social Policy ------------------------------------------------------------------------ _______________________________________________ gov2001-l mailing list gov2001-l at lists.fas.harvard.edu http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l

-- Holger Lutz Kern Ph.D. cand. Department of Government Cornell University Institute for Quantitative Social Science Harvard University 1737 Cambridge Street N350 Cambridge, MA 02138 www.people.cornell.edu/pages/hlk23

Reply

king＠harvard.edu

4:24 p.m.

that's a reasonable way to proceed. another is to match exactly on the actual values, including the NAs. and there are other ways. no one has really done research on this, so its a bit of a hack. Gary On Tue, 1 May 2007, Holger Lutz Kern wrote:

Miya, I think the correct order is to first impute, then match within each imputed dataset. Otherwise you would have to deal with the NAs during the matching. Holger Miya Woolfalk wrote:

Hi, If we want to both impute and match, what is the best order for doing these procedures? There has been some disagreement about this. Is it appropriate to match on imputed data? Thanks, Miya -- K. Miya Woolfalk Graduate Student Harvard University Government and Social Policy ------------------------------------------------------------------------ _______________________________________________ gov2001-l mailing list gov2001-l at lists.fas.harvard.edu http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l

Reply

6227

days inactive

6227

days old

gov2001@lists.gking.harvard.edu

Manage subscription

2 comments

3 participants

tags (0)

participants (3)

hlk23＠cornell.edu
king＠harvard.edu
woolfalk＠fas.harvard.edu