So if I am running the t-test two-tailed, and have adjusted my
threshold accordingly already, than the f-test is now overly
stringent... does the f-test so something other than a 2-tailed t-test
would in this situation?
thanks. this has been very helpful.
On Dec 5, 2006, at 3:07 AM, Tim Behrens wrote:
> Just to add -
> You might see significance in C1, but not in F1, as
> C1 is a 1-tailed test, but F1 is not sensitive to the sign of the
> effect (positive or negative)
> so it is effectively doing a 2-tailed test.
>
> If you double the p-value for the F-test, you should see all the
> voxels in C1 reappear (+some more for the opposite contrast)
>
> T
>
> On 5 Dec 2006, at 10:10, Steve Smith wrote:
>
>> In such simple (single-contrast) f-tests, the f is effectively the
>> _square_ of the t, so will show +ve and -ve significant values.
>> 3) is correct, yes.
>> Cheers, Steve.
>>
>> On 5 Dec 2006, at 00:22, Jennifer Bramen wrote:
>>
>>> Hi All,
>>>
>>> I am trying to understand how to readd the results of a 2x2 ANOVA.
>>>
>>> F1 F2 F3
>>> OC1 [1 0 0] x
>>> OC2 [0 1 0] x
>>> OC3 [0 0 1] x
>>>
>>> Where I think
>>> C1 = Main Positiove Effect of A
>>> C2 = Main Positive Effect of B
>>> C3 = Interaction of A and B
>>>
>>> What are the f-tests exactly? I thought, for example, that F1 was a
>>> map of [1 00] OR [-1 0 0], but I
>>> see significance in C1 but not in F1... so clearly I am mistaken.
>>>
>>> 1) Am I interpreting the Contrasts correctly.
>>> 2) How do I interpret f-tests?
>>> 3) If I want to see a negative effect of factor A, for example,
>>> (where level 2 > Level 1), would I use
>>> [-1 00]?
>>>
>>> Thanks for the clarification.
>>
>>
>> ----------------------------------------------------------------------
>> -----
>> Stephen M. Smith, Professor of Biomedical Engineering
>> Associate Director, Oxford University FMRIB Centre
>>
>> FMRIB, JR Hospital, Headington, Oxford OX3 9DU, UK
>> +44 (0) 1865 222726 (fax 222717)
>> [log in to unmask] http://www.fmrib.ox.ac.uk/~steve
>> ----------------------------------------------------------------------
>> -----
>
>
Jennifer Bramen
UCLA Brain Mapping Center
660 Charles Young Dr. So
Los Angeles, CA 90095
----------------------------------------------------------
IMPORTANT WARNING: This email (and any attachments) is only intended for the use of the person or entity to which it is addressed, and may contain information that is privileged and confidential. You, the recipient, are obligated to maintain it in a safe, secure and confidential manner. Unauthorized redisclosure or failure to maintain confidentiality may subject you to federal and state penalties. If you are not the recipient, please immediately notify us by return email, and delete this message from your computer.
----------------------------------------------------------
|