Date:         Tue, 29 Sep 2009 09:18:28 -0700
Reply-To:     Sassy <augustinao@GMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Sassy <augustinao@GMAIL.COM>
Organization: http://groups.google.com
Subject:      McNemar's for 1 to 3 matched pairs
Comments: To: sas-l@uga.edu
Content-Type: text/plain; charset=ISO-8859-1

Hi All,

I did a propensity score matching analysis using a 1 to 3 match.  I
have both binary and continuous outcomes. For the binary outcome, i
want to use a McNemar's test.  So far all of the reference I have come
across only used it for a 1 to 1 match.  Is it appropriate to use when
you are doing a 1 to many match?  If not, can anyone suggest an
appropriate test to use?  Also for the continuous outcome, is a paired
ttest appropriate?

Thanks!!!