Re: SPSS and Regression
- From: Marc Halbruegge <marc.halbruegge@xxxxxx>
- Date: Sat, 25 Mar 2006 16:57:16 +0100
Y=Beta+B1X1+B2G1+B3G2+B4(G1*X1)+B5(G2*X1)+E
Yes, your interpretation is correct (IMHO).
My result shows a significant overall model and a significant
interaction G1*X1 with a -t value and p=0.006.
Is this an appropriate interpretation: Since G1 represents group1
(because grp2 and control=0) does this mean that as Y increases, G1
decreases for group 1 only? If so, what is happening in the control
group? How can I know?
As you have used dummy coding, B1 is telling you what's going on in the
control group. If you had used effect coding ((1,0,-1),(0,1,-1)), then
B1 would be the overall effect.
.
- References:
- SPSS and Regression
- From: teresa . realpe
- Re: SPSS and Regression
- From: Reef Fish
- Re: SPSS and Regression
- From: teresa . realpe
- Re: SPSS and Regression
- From: Reef Fish
- Re: SPSS and Regression
- From: teresa . realpe
- Re: SPSS and Regression
- From: Bruce Weaver
- Re: SPSS and Regression
- From: teresa . realpe
- SPSS and Regression
- Prev by Date: multicollinearity in regression
- Next by Date: Re: multicollinearity in regression
- Previous by thread: Re: SPSS and Regression
- Next by thread: Missing cases...what to do?
- Index(es):