Date:         Mon, 29 Oct 2007 11:41:50 -0700
Reply-To:     Dale Glaser <glaserconsult@sbcglobal.net>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Dale Glaser <glaserconsult@sbcglobal.net>
Subject:      Multivariate regression: MANOVA vs. GLM
In-Reply-To:  <200710291641.l9TAlABb013772@mailgw.cc.uga.edu>
Content-Type: text/plain; charset=iso-8859-1

Hi all...using MANOVA syntax I have been able to run a multivariate regression as follows:

  MANOVA DV1 DV2 DV3 DV4 WITH Cov1 Cov2 Cov3
  /print=cellinfo(means, cor)
  /print=signif(singledf).

  .and I derive the appropriate multivariate tests of significance for the full complement of explanatory and response variables..however, trying to do the same with GLM:

  GLM
    DV1 DV2 DV3 DV4 WITH Cov1 Cov2 Cov3
    /METHOD = SSTYPE(3)
    /INTERCEPT = INCLUDE
   /PRINT = DESCRIPTIVE ETASQ PARAMETER TEST(SSCP) RSSCP
    /CRITERIA = ALPHA(.05)
    /DESIGN = Cov1 Cov2 Cov3.

  I only get a multivariate test for the linear combination of each DV's for each separate IV.......I have thoroughly scoured the syntax manual but can't seem to engineer the output in GLM to get the same omnibus multivariate test (i.e., combination of multiple response AND explanatory variables) that I get in MANOVA

  suggestions?...........thank you....dale




Dale Glaser, Ph.D.
Principal--Glaser Consulting
Lecturer/Adjunct Faculty--SDSU/USD/AIU
President, San Diego Chapter of
American Statistical Association
3115 4th Avenue
San Diego, CA 92103
phone: 619-220-0602
fax: 619-220-0412
email: glaserconsult@sbcglobal.net
website: www.glaserconsult.com

=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD