Date:         Tue, 1 May 2001 19:23:41 -0500
Reply-To:     Annette Towler <towleraj@RICE.EDU>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Annette Towler <towleraj@RICE.EDU>
Subject:      canonical correlations in manova
Content-Type: text/plain; charset="us-ascii"; format=flowed

Dear SPSSers

I have a repeated-measures design with 6 groups (stigma) and 2 measures
(evaluation and comfortability). In a previous analysis I was able to use
MANOVA and obtain the canonical correlations in SPSS. I am now using GLM
and cannot obtain this function. In MANOVA, the syntax is

Manova....
/discrim = (raw, stan, estim, cor)
/print = signif (eigen,  dimenr)


How do I obtain this in GLM? My syntax in GLM is:

GLM
   physcom attrcom confcom mentcom racecom sexcom physeva attreva confeva
   menteva raceeva sexeva
   /WSFACTOR = sitgma 6 Polynomial
   /MEASURE = com eva
   /METHOD = SSTYPE(3)
   /PRINT = DESCRIPTIVE ETASQ
   /CRITERIA = ALPHA(.05)
   /WSDESIGN = sitgma .

Thanks, Annette.