Contrast 1: Positive correlation for age after controlling for X
Contrast 2: Positive correlation for X after controlling for age
Contrast 3/4: Meaningless since the difference in the slop of the 2
covariates is usually uninterpretable. You'd have to have the same
variance in both covariates to make them interpretable in a contrast.
For example. age and weight slopes couldn't be compared as both of
them have different scales and different variances.
Best Regards, Donald McLaren
=================
D.G. McLaren, Ph.D.
Research Fellow, Department of Neurology, Massachusetts General Hospital and
Harvard Medical School
Postdoctoral Research Fellow, GRECC, Bedford VA
Website: http://www.martinos.org/~mclaren
Office: (773) 406-2464
=====================
This e-mail contains CONFIDENTIAL INFORMATION which may contain PROTECTED
HEALTHCARE INFORMATION and may also be LEGALLY PRIVILEGED and which is
intended only for the use of the individual or entity named above. If the
reader of the e-mail is not the intended recipient or the employee or agent
responsible for delivering it to the intended recipient, you are hereby
notified that you are in possession of confidential and privileged
information. Any unauthorized use, disclosure, copying or the taking of any
action in reliance on the contents of this information is strictly
prohibited and may be unlawful. If you have received this e-mail
unintentionally, please immediately notify the sender via telephone at (773)
406-2464 or email.
On Wed, Jan 30, 2013 at 12:51 PM, Kailyn Bradley
<[log in to unmask]> wrote:
> Dear SPM users,
>
> I have a question about how to interpret contrasts when there are two
> covariates in a second level multiple regression analysis.
>
> Here is a little info about my design:
>
> I am examining activation during single word reading in two groups of
> bilinguals, adults and children, in both languages that they speak (English,
> Spanish). I want to see if the activity I am seeing is related to stage in
> development (i.e. age) and/or language proficiency differences.
>
> I have set up a second level multiple regression analysis and input the
> scans for all subjects (adults and children) for the contrast at the first
> level I am interested in (English > baseline). Next, I input two covariates
> into the model: age and English proficiency.
>
> The problem I am having is how to interpret the contrasts I am entering when
> there are two covariates in my model. I think that if I just had one
> covariate in the model, for example, age, then a contrast of (1) would
> indicate the positive correlation between my covariate, age, and the BOLD
> signal, and (-1) would indicate the negative correlation. However, when I
> have two covariates in the model, how do I interpret the following contrasts
> if the first covariate is age and the second is proficiency?
>
> 1 0
>
> 0 1
>
> 1 -1
>
> -1 1
>
> Any help would be greatly appreciated.
>
> Thank you,
> Kailyn
|