Date: Thu, 23 Jan 2003 14:22:16 -0500
Reply-To: Tara West <twest4@HOTMAIL.COM>
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: Tara West <twest4@HOTMAIL.COM>
Subject: path analysis with contrasts
Content-Type: text/html
<html><div style='background-color:'><DIV>
<P><BR>Dear Listserve members:</P>
<P>I ran a study with 5 groups (conditions that were randomly assigned), but am running planned contrasts with just 2 groups at a time. I can do this on SPSS by doing a one-way ANOVA with contrasts, which also takes into account the error from the other groups. However, I am also conducting a path analysis, so I need to test mediation (boht the DV and mediator are continuous variables). I was able to do an analysis with SAS to find the relation between the IV contrast and the DV (t, probability parameter estimate, and standard error), controlling for the mediatory, but am having a hard time figuring out how to do it the other way around (mediator to DV, controlling for the IV, which is the condition variable as a contrast). To get the path I already found, with the variables being IV: conditio; DV: wlhlptot; & mediator: athmsoto, contrasting conditions 1 & 3 of the IV, the key commands I used were: proc glm data=b.taradat; class conditio; model wlhlptot=conditio athmsoto; LSMEANS CONDITIO ; CONTRAST 'COND1 VS COND3' CONDITIO 1 0 -1 /e; ESTIMATE 'COND1 VS COND3' CONDITIO 1 0 -1. I would have assumed that the other analysis would be the same, but I can't seem to get the values (t, etc..) for the other path. If anyone could help me figure out a way to do that, I would greatly appreciate it. </P>
<P>Thank you,</P>
<P>Tara West<BR></P></DIV>
<DIV></DIV><BR><BR><BR>
<DIV></DIV>
<DIV> </DIV>
<DIV></DIV>
<DIV>Tara West</DIV>
<DIV></DIV>
<DIV>Department of Psychology </DIV>
<DIV></DIV>
<DIV>State University of New York at Stony Brook</DIV>
<DIV></DIV>
<DIV>Stony Brook, NY 11794-2500</DIV>
<DIV></DIV>
<DIV>Phone: (631) 632-4473 fax: (631) 632-7876</DIV>
<DIV></DIV>
<DIV> </DIV>
<DIV></DIV>
<DIV></DIV></div><br clear=all><hr>Add photos to your e-mail with <a href="http://g.msn.com/8HMHENUS/2746">MSN 8.</a> Get 2 months FREE*.</html>
| 
