Print

Print


Omar,

Since your models are different, they will give a different result. This is not a surprise.

There are several differences/potential differences:
(1) In the t-test, you assumed that the effect of diagnosis had the same effect for both genotypes (1 covariate);
(2) In the t-test, you might not have set the variance to unequal;
(3) Differences in the design matrix leads to different degrees of freedom and a different residual error.

As has been said before on the list. You first need to develop your research question and then select the model that will best answer the question. Without knowing your question, its hard to assess which model would be better. 

Best Regards, Donald McLaren
=================
D.G. McLaren, Ph.D.
Postdoctoral Research Fellow, GRECC, Bedford VA
Research Fellow, Department of Neurology, Massachusetts General Hospital and
Harvard Medical School
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 Mon, Jun 25, 2012 at 5:49 AM, Omar Mothersill <[log in to unmask]> wrote:
Dear SPM users,

In SPM 8, I used an independent t-test to compare two genotype groups on a task, and I included a categorical covariate (control or patient) in the model.  As an alternative, I also tried a full factorial with two factors, diagnosis and genotype.  However, these tests give completely different results, and I'm not sure why.  I set the full factorial as follows:

Factor 1 (genotype):
Levels - 2
Independence - Yes
Variance - Unequal

Factor 2 (diagnosis):
Levels - 2
Independence - Yes
Variance - Unequal

If anyone has any advice it would be greatly appreciated.  I've also included the design matrix for the full factorial model, perhaps there is a problem with it?

Kind regards,

Omar Mothersill


--
Omar Mothersill

Room 0.18
Neuropsychiatric Genetics Group
Dept. of Psychiatry
Trinity Centre for Health Sciences
St. James's Hospital
Dublin 8.

Phone: 01 896 2464
Email: [log in to unmask]