This is expected. You have done nothing wrong.
The following are all equivalent:
(G1C1>G1C2)>(G2C1>GC2) [t-test of con3]
(G1C1-G1C2)-(G2C1-G2C2)
G1C1+G2C2-G1C2-G2C1
G2C2-G2C1+G1C1-G1C2
(G2C2-G2C1)-(G1C2-G1C1)
(G2C2>G2C1)>(G1C2>G1C1) [t-test of con4]
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 Thu, Apr 19, 2012 at 5:05 AM, Lara Schlaffke <[log in to unmask]> wrote:
> Dear SPMer,
>
> I have a question relating to the statistical analyses of my study. For the study I have 2 different groups of subjects (G1 & G2) and 3 different conditions during the fMRI (C1, C2 and Control) In the first level analyses I did 4 t-tests for each subject (con01: C1>Control; con02: C2>Control; con03: C1>C2 and con04: C2>C1).
>
> The contrast vectors were as following: [1 0 -1] for Con01; [0 1 -1] for con02; [1 -1 0] for Con03 and [-1 1 0] To do the 2nd Level (between group) analyses I did a 2-sample t-test for each contrast (con01, con02, con03, con04) in which I added the respective con-images of both groups. After this calculation I have the option to decide whether I want to see Group 1 > Group2 OR Group2 >Group1.
>
> And now my problem: The results of the 2 contrasts Con03(C1>C2) G1>G2 AND Con04(C2>C1) G2>G1 were exactly the same (i.e. they showed exactly the same activated areas in the glass brain and in the list of activated regions), as was the case for both in the oposite direction (Con03(C1>C2) G2>G1 AND Con04(C2>C1) G1>G2. This does not make sense to me.
>
> Do you have any idea how I could analyze or rework either the data groups or the experimental design so to get more reasonable statistical results?
>
> Thanks
>
> Lara
|