Date:         Wed, 7 Jul 1999 14:08:02 -0500
Reply-To:     "Nichols, David" <nichols@SPSS.COM>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "Nichols, David" <nichols@SPSS.COM>
Subject:      Re: simple main effects

In this context, the repeated measures don't come into play, other than that
you have to understand that the between subjects results are done on the
average over the levels of the repeated factor. The covariate doesn't alter
the command syntax requirements, and you're looking at simple effects
involving adjusted means. Thus, the principles in the article hold for this
case. The command would be:

MANOVA
  totpro_1  totpro_2  BY delivery(1 2) dichmast(1 2) organize(1 2)
WITH(totper_1)
  /WSFACTORS time(2)
  /METHOD UNIQUE
  /ERROR WITHIN+RESIDUAL
  /POWER T(.05) F(.05)
  /PRINT SIGNIF( MULT AVERF EFSIZE  )cellinfo (means)
  /NOPRINT PARAM(ESTIM)
  /DESIGN=dichmast, delivery, organize,
          dichmast*delivery, dichmast*organize,
          delivery*organize w dichmast(1),
          delivery*organize w dichmast(2).

David Nichols
Principal Support Statistician and
Manager of Statistical Support
SPSS Inc.

> -----Original Message-----
> From: Annette Towler [mailto:towleraj@RUF.RICE.EDU]
> Sent: Thursday, July 01, 1999 10:31 AM
> To: SPSSX-L@LISTSERV.UGA.EDU
> Subject: simple main effects
>
>
> Hi SPSSERS
>
> I have a mixed factorial design and have a three-way
> interaction (delivery
> x dichmast x organize). I want to do followup comparisons
> using the simple
> effects procedure looking at delivery x organize at each
> level of dichmast.
> Dave Nichols's paper on simple main effects is very useful,
> but I am unsure
> on the syntax to use when I have a covariate and a repeated measures
> design. Thanks in advance. Here is my syntax for the overall design:
>
>
> MANOVA
>   totpro_1  totpro_2  BY delivery(1 2) dichmast(1 2) organize(1 2)
> WITH(totper_1)
>   /WSFACTORS time(2)
>   /METHOD UNIQUE
>   /ERROR WITHIN+RESIDUAL
>   /POWER T(.05) F(.05)
>   /PRINT SIGNIF( MULT AVERF EFSIZE  )cellinfo (means)
>   /NOPRINT PARAM(ESTIM) .
> Annette Towler
> Psychology Department
> Rice University
> 466 Sewall Hall, MS 25
> 6100 Main
> Houston, Texas  77005-1892
>