It would depend on how you structured your
regression. Could you print that syntax?
Notice that you are using Type III ANOVA. The
regression to match that would be to have the 2 main and the interaction effect
all in the same block.
Joe Burleson
From: SPSSX(r)
Discussion [mailto:[hidden email]] On
Behalf Of Salbod, Mr. Stephen
Sent: Thursday, February 12, 2009
3:46 PM
To: [hidden email]
Subject: Continuous Variable and
ANOVA
Dear
Friends,
I keep getting different results when I try to demonstrate that ANOVA gives the
same results as Regression. I am using a continuous predictor; I’m not
sure whether I specified the correct analysis in UNIANOVA.
The
outcome variable is a scale score (Scale-Continuous). The two predictors are
Gender (Dichotomy) and Age (Continuous) .
I
had no problem with the regression. I centered age; DEPENDENT=scale;
METHOD=ENTER gender age gender*age .
However,
I’m not sure about the ANOVA. Here is my syntax:
UNIANOVA
Scale BY Gender WITH Age
/METHOD=SSTYPE(3)
/INTERCEPT=INCLUDE
/PRINT=DESCRIPTIVE
/CRITERIA=ALPHA(.05)
/DESIGN= Gender Age Gender*Age.
Any
suggestions or references will be greatly appreciated.
Many
thanks in advance for your help,
Stephen Salbod, Pace University,
NYC
Locked
