Date:         Thu, 21 May 1998 12:40:41 -0500
Reply-To:     "Nichols, David" <nichols@SPSS.COM>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From:         "Nichols, David" <nichols@SPSS.COM>
Subject:      Re: UNIANOVA and partial eta squared
Comments: To: Dale Glaser <dale.glaser@SHARP.COM>

MANOVA only gives eta^2 when you asked for SEQUENTIAL sums of squares. You
can still get that using MANOVA through syntax. The eta^2 in GLM is indeed
the partial eta^2.
 
David Nichols
Principal Support Statistician and
Manager of Statistical Support
SPSS Inc.
nichols@spss.com
 
----------
From:  Dale Glaser [SMTP:dale.glaser@SHARP.COM]
Sent:  Monday, May 18, 1998 4:27 PM
To:  SPSSX-L@UGA.CC.UGA.EDU
Subject:  UNIANOVA and partial eta squared
 
Hi there...quick question....in the old MANOVA procedure when testing
for a two-way interaction (for a general factorial design), both partial
eta
squared and eta squared were included in the ouput.......however, in
UNIANOVA (SPSS 8.0) only the eta squared is reported, even though
technically it is the partial eta squared, as calculations will show that
the
sum of squares of the other effects are partialed out.........so is there
a
way (outside of doing the obvious hand calculations:
i.e.,    (sum of squares/corrected model sum of squares)
for each of the main effects/interaction terms, that I can derive the eta
squared like the old MANOVA procedure?
 
thank you..................dale glaser