[pymvpa] classification project

[Abduljalil Sireis]

Hello,

I want to get some help regarding GLM.

The GLM analysis that needs to be performed to get the beta estimates is a
multiple regression analysis. In other words, I need  to specify a model
that includes predictors (one predictor for each condition, a confound-mean
predictor (all-one vector), and optionally head-motion and trend
predictors), and then fit this model to the data to obtain the
beta-estimates.


*TR (scan repeat time) = 3000 ms. Functional measurement consisted of 220
scans.*

Attached with this email the table of Onsets and Durations for both
conditions. There are also indices of the conditions but for me they are
not logical as they don't really correspond to the timings. Anyway, I have
an important question. What about the number of scans for each condition
and also for the rest condition? The durations are real numbers and if i
try to divid the number by 3 (which is TR) i get  real number of scans, so
i'm not exactly sure of the number of 1s and 0s in the model.

It is needed to convolve the model with gamma function, how this could be
done? What about the parameters of gamma function? I also don't know how to
do the additional and confound-mean predictors.

Thanks in advance,
Abdul

On Wed, Sep 19, 2012 at 5:52 PM, Mike E. Klein <michaeleklein at gmail.com>wrote:

> www.princeton.edu/~matthewb/Publications/<http://www.princeton.edu/%7Ematthewb/Publications/>
> *tutorial*.pdf
>
> http://scan.oxfordjournals.org/content/4/1/101.full
>
> www.bcn-nic.nl/txt/people/publications/*Etzel*2009.pdf
>
> On Wed, Sep 19, 2012 at 11:22 AM, Abduljalil Sireis <kentman234 at gmail.com>wrote:
>
>>
>>
>> On Wed, Sep 19, 2012 at 4:56 PM, J.A. Etzel <jetzel at artsci.wustl.edu>wrote:
>>
>>> This is far too general of a question: which steps are necessary depends
>>> upon the precise hypothesis you're testing with the analysis. I can easily
>>> think of a half dozen analysis schemes appropriate in various situations.
>>>
>>> You should start by making your hypothesis as concrete as possible. For
>>> example, are you interested in widespread activity, or activity in
>>> particular brain areas only? Are you interested in activity during
>>> particular times during the clips, or some sort of temporally averaged
>>> activity?
>>>
>>
>> - I'm interested in particular brain areas or regions of interest which
>> should be activated during the experiment. Also, a temporally averaged
>> activity would be fine.
>>
>>
>>>
>>> There are many useful tutorials; the ones by Pereira, Mur, and (if I say
>>> so myself) Etzel are good starting points.
>>>
>>
>> - Which tutorial do you mean? Could you please write me its name or the
>> link or it?  Thank you!
>>
>>>
>>> good luck,
>>> Jo
>>>
>>>
>>>
>>> On 9/19/2012 7:19 AM, Abduljalil Sireis wrote:
>>>
>>>> Hi,
>>>>
>>>> I need help  in classification project of subjects see two types of
>>>> video clips. One kind is dangerous car accidents and the other is normal
>>>> car advertisements. We have number of subjects perform this task with
>>>> one session per subject. Each run consists of 6 clips from each type,the
>>>> two successive spots are separated by black screen and a yellow cross to
>>>> fix the subjects eyes. There was not a specific order of the spots but
>>>> more than two successive ones of the same type were not allowed. All
>>>> videos were accompanied with voice, so we have visual and audio
>>>> stimulation.
>>>>
>>>> I think that i need to do features selection with respect to the active
>>>> regions corresponding to the stimulations, then a cross-validation leave
>>>> one-run-out can be applied. Could you please guide me through this
>>>> project? Which concrete steps should i need to do?
>>>>
>>>> Thank you,
>>>> Abdul
>>>>
>>>>
>>>> ______________________________**_________________
>>>> Pkg-ExpPsy-PyMVPA mailing list
>>>> Pkg-ExpPsy-PyMVPA at lists.**alioth.debian.org<Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org>
>>>> http://lists.alioth.debian.**org/cgi-bin/mailman/listinfo/**
>>>> pkg-exppsy-pymvpa<http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa>
>>>>
>>>>
>>> --
>>> Joset A. Etzel, Ph.D.
>>> Research Analyst
>>> Cognitive Control & Psychopathology Lab
>>> Washington University in St. Louis
>>> http://mvpa.blogspot.com/
>>>
>>> ______________________________**_________________
>>> Pkg-ExpPsy-PyMVPA mailing list
>>> Pkg-ExpPsy-PyMVPA at lists.**alioth.debian.org<Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org>
>>> http://lists.alioth.debian.**org/cgi-bin/mailman/listinfo/**
>>> pkg-exppsy-pymvpa<http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa>
>>>
>>
>>
>> _______________________________________________
>> Pkg-ExpPsy-PyMVPA mailing list
>> Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
>> http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa
>>
>
>
> _______________________________________________
> Pkg-ExpPsy-PyMVPA mailing list
> Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
> http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20121126/67918143/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Onsets and Durations.docx
Type: application/vnd.openxmlformats-officedocument.wordprocessingml.document
Size: 14178 bytes
Desc: not available
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20121126/67918143/attachment-0001.docx>