Date:         Thu, 22 Jan 2009 14:29:07 -0500
Reply-To:     "P. Cristian Gugiu" <crisgugiu@YAHOO.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "P. Cristian Gugiu" <crisgugiu@YAHOO.COM>
Subject:      Re: Matched-Group Design

Robin,

Thanks for the suggestions. I'm curious to know if the three different
methods will all converge upon the same conclusion. I was planning on
bootstraping Proc GLM anyway, so I will include the two solutions that you
proposed. One question, can you tell me what option I need to use to
output the p-values for Proc Mixed? For instance, in Proc GLM I can output
the a dataset with the p-values for type 3 using

proc glm data=Matched OUTSTAT=P1(where=(_type_ ne "SS1")) noprint ;


thanks,
Cristian