Would running "Mixed Effects Stage 1 only" lead to incorrect results when
used for combining the single subject runs (maybe only to be used when
combining runs from multiple subjects with run as a repeated and subject as
random factor)?
Tx, Theo
on 10/17/05 7:46 AM, Stephen Smith at [log in to unmask] wrote:
> Hi Theo, yes, this all makes sense:
>
> You can either follow the mixed inputs instructions at:
> http://www.fmrib.ox.ac.uk/fslfaq/#feat_mixedup
>
> Or just run a "fake" 2nd level on these single cases using fixed-effects
> (though you'll need to save the design.fsf and edit it by hand to change
> the number of inputs to 1).
>
> Cheers. Steve.
>
>
>
> On Thu, 13 Oct 2005, Theo van Erp wrote:
>
>> Hi,
>>
>> I have another question related to empty EVs. I'm working on a single trial
>> study with multiple runs and analyses based on subject responses.
>>
>> Sometimes there are missing EVs because a subject did not make a certain
>> type of response. This is not a problem, since as suggested below I then
>> leave out the empty Evs and leave the contrast order the same. I put zeros
>> for the non-existent contrasts (due to the missing EV) and correct the
>> contrasts to account for having fewer EVs. This appears to generate empty
>> (0) copes, and I then combine only the non-empty copes in a 2nd level
>> analysis to create 1 cope per subject to be included in a 3rd level
>> analysis.
>>
>> However, I'm running into a problem when a contrast only exists in 1 run
>> (you can't do a 2nd level, since the dof would be 0). Should I in this case
>> just register the cope from one individual run to standard space in the
>> first level analysis such that I can include it into a 3rd level analysis or
>> does this somehow mess up the dofs?
>>
>> I'll try a couple of things, but any feedback would be appreciated.
>>
>> Best, Theo
>>
>> on 6/5/04 12:17 PM, Mark Jenkinson at [log in to unmask] wrote:
>>
>>> Hi,
>>>
>>> This depends on what contrasts you are trying to use.
>>> If you have a contrast that only contains "missing" EVs then
>>> you can't have this if you drop these EVs. However, I'm
>>> assuming that the contrasts of interest for the group analysis
>>> are not going to include only missing EVs for any subject or
>>> session. Otherwise there is no information that this subject
>>> or session can contribute to the group analysis in this case
>>> and just shouldn't be included for the higher level analysis.
>>>
>>> If you do make contrasts to see certain effects in the lower
>>> level analysis that you don't pass up to the group analysis
>>> (e.g. a 0 0 1 0 0 ... 0 type contrast for each EV) then it doesn't
>>> matter what you put in this place for the lower level analysis
>>> as far as the group analysis is concerned.
>>>
>>> The best approach for you is probably to restrict yourself to
>>> first level analyses that only contain the contrast of interest
>>> for the group analysis. This should include at least one
>>> non-missing EV for each session/subject (if not, exclude
>>> that session/subject from the group analysis). Once you've
>>> done this the group analysis is straightforward.
>>>
>>> If you are interested in looking at other contrasts in the lower
>>> level, you can always run different contrasts again under
>>> post-stats to have a look (which is quick and easy).
>>>
>>> All the best,
>>> Mark
>>>
>>>
>>> On Thursday, June 3, 2004, at 10:42 pm, Sam Harris wrote:
>>>
>>>> Hi, Mark
>>>>
>>>> Thanks for your response. It seems to me, however, that I'm not out of
>>>> the woods yet--because once I drop the missing EVs for any given run,
>>>> that run will then not have the same number of contrasts.
>>>> Have I misunderstood you somewhere?
>>>>
>>>> Best,
>>>> Sam
>>>>
>>>> On Jun 3, 2004, at 11:15 AM, Mark Jenkinson wrote:
>>>>
>>>>> Hi,
>>>>>
>>>>> What you really need to do is create consistent *contrasts* not EVs.
>>>>> It is contrasts that get fed up into the higher level analyses, not
>>>>> EVs.
>>>>> If an EV is missing, then do not have it in the model. However, when
>>>>> formulating your contrasts make sure that the numbering of the
>>>>> contrasts
>>>>> is the same in each subject/session so that these feed up
>>>>> consistently.
>>>>>
>>>>> You'll have to be careful to select the appropriate EVs each time, as
>>>>> their numbering will change whenever some are missing.
>>>>> For example, if you had a contrast like 1 0 -1 0 0 1 0 and in one case
>>>>> EV2 was missing then the design matrix would only have 6 columns,
>>>>> not 7, and the contrast would become 1 -1 0 0 1 0 in this
>>>>> instance (assuming the other EVs were present).
>>>>>
>>>>> Obviously these missing EVs cannot contribute to the contrast, but
>>>>> as long as each contrast contains at least one EV then you are fine.
>>>>>
>>>>> All the best,
>>>>> Mark
>>>>>
>>>>>
>>>>> Sam Harris wrote:
>>>>>
>>>>>> I'm attempting to analyze event-related data acquired on 14 subjects,
>>>>>> 3 runs each, in which
>>>>>> certain EVs, in any given run, were not represented. For example,
>>>>>> subject #6, in run #2, may not
>>>>>> have provided a single example of EV 8 (while all other subjects did,
>>>>>> as did subject #6 himself in
>>>>>> runs 1 and 3). I'm wondering if there is any way of creating a
>>>>>> "place-holder" model (in three-
>>>>>> column format), so that all subjects and all runs can contain the
>>>>>> same number of EVs, thereby
>>>>>> allowing analysis at the group level. Could I, in the above case,
>>>>>> create a spurious model for EV 8
>>>>>> (in subject #6, run #2), with a fictional onset time and duration,
>>>>>> and scale it at (or near) 0? Or
>>>>>> could I create an extra volume, tacked onto to the end of all scans,
>>>>>> that represented the average
>>>>>> value of each functional run, and then reference this timepoint in my
>>>>>> model as a dummy-EV?
>>>>>> Needless to say, I'm looking for a solution that will produce, in the
>>>>>> worst case, a type 2 error.
>>>>>>
>>>>>> Thanks for your help.
>>>>>> Sam
>>>>>>
>>>>>>
>>>>>
>>>
>>
>> _____________________________________________________________
>> Theo van Erp
>> Lab Manager, PhD Candidate
>>
>> Cannon Lab
>> Department of Psychology [log in to unmask]
>> University of California Los Angeles voice (310) 794-9673
>> 1285 Franz Hall, room 5556 fax (310) 794-9740
>> Los Angeles, California, 90095-1563
>> http://www.bol.ucla.edu/~vanerp
>> _____________________________________________________________
>>
Best, Theo
_____________________________________________________________
Theo van Erp
Lab Manager, PhD Candidate
Cannon Lab
Department of Psychology [log in to unmask]
University of California Los Angeles voice (310) 794-9673
1285 Franz Hall, room 5556 fax (310) 794-9740
Los Angeles, California, 90095-1563
http://www.bol.ucla.edu/~vanerp
_____________________________________________________________
|