[pymvpa] glm for MVPA
basile pinsard
basile.pinsard at gmail.com
Mon Feb 15 20:43:01 UTC 2016
Thanks for your quick reply.
Certainly that any normalization of the betas increases the classification
accuracy.
My model is different, for example if I want to model a instruction event,
I have a regressor for this event, another regressor for all other
instruction events, and one regressor for all the execution events (+ a
constant).
As execution directly follows the stimuli end, (with reaction time), the
regressors sure overlaps and might cause wrong estimates.
About the model, I have more questions in fact.
The fact that there is a subject's response makes the duration of events
unequals and instruction is a 4sec stimuli.
I have modelled the instruction and execution phases as blocks instead, but
it might bias the samples depending on the difficulty of trials causing
longer execution and thus more TR to estimate on.
Do you think I should consider all phases as events and perform a
event-related design or use a block design?
I have also been using raw data instead of GLM based samples, but sure the
signal to noise is a bit high.
Thanks.
basile
On Mon, Feb 15, 2016 at 11:07 AM, Christopher J Markiewicz <effigies at bu.edu>
wrote:
> On 02/15/2016 10:20 AM, basile pinsard wrote:
> > Hi pymvpa users and developers.
> >
> > I have multiple questions regarding the use of GLM to model events for
> > MVPA analysis which are not limited to PyMVPA.
> >
> > First: in NiPy GLM mapper the measure extracted are beta weights from
> > GLM fit
> > <
> https://github.com/bpinsard/PyMVPA/blob/master/mvpa2/mappers/glm/nipy_glm.py#L50
> >,
> > is that common for MVPA? StatsModelGLM mappers return t-p-z... values
> > from model. Does using the t-statistic is more relevant?
> > The following paper Decoding information in the human hippocampus
> > <http://www.sciencedirect.com/science/article/pii/S0028393212002953>: A
> > user's guide says: "In summary, the pre-processing method of choice at
> > present appears to be the use of the GLM to produce /t/-values as the
> > input to MVPA analyses. However, it is important to note that this does
> > not invalidate the use of other approaches such as raw BOLD or betas,
> > rather the evidence suggests that these approaches may be sub-optimal,
> > reducing the power of the analysis, making it more difficult to observe
> > significant results."
> > What do you think?
>
> I don't remember reading the referenced article, but I've done a little
> playing in this area. While I haven't done per-event t-scores, I have
> done one t-statistic per-condition-per-run, and found very similar
> spatial pattern of results to those from per-event betas, but with much
> higher classification accuracy. For whatever that's worth.
>
> With per-event betas (z-scored using the ZScoreMapper built on control
> conditions), I get distributions of CV accuracies around chance, which
> is fine for our analysis strategy. Personally, I don't quite know what
> to make of ~50% minimum classification on a problem where chance is 33%.
> That said, we use non-parametric significance testing, while there may
> be parametric methods that work better on t-score-based MVPA.
>
> Not sure if that's relevant to you, but that's what I think. :-)
>
> > Second: I have developed another custom method to use
> > Least-square-separate (LS-S) model that uses 1 model for each
> > event/block/regressor of interest as shown to provide more stable
> > estimates of the patterns and improved classification in Mumford et al
> > 2012. However for each block I want to model 2 regressors, 1 for
> > instruction and 1 for execution phases which are consecutive. So the
> > procedure I use is 1 regressor for the block/phase that I want to model
> > + 1 regressor for each phase, is that correct?
>
> I've used a similar strategy, also inspired by the Mumford, et al paper.
> I'm not sure if I'm understanding you correctly, so I'll just describe
> my approach:
>
> Each trial has an A event and a B event, and is described by a single
> stimulus type. If I have 8 trial types, then I have 16 "conditions"
> [(cond1, A), (cond1, B), ...]. For each condition, I perform one
> least-squares estimate: one column for each condition of non-interest,
> and the condition of interest expanded into one column per event.
>
> It sounds like you might be doing something slightly different?
>
> > I would be interested to include these in PyMVPA in the future, as the
> > LS-A (stands for All) is not adequate in rapid event design with
> > correlated regressors.
>
> Since it turns out I'm not the only one who's needed to develop this,
> this seems like a good idea to me. If you're interested in my input, you
> can ping me on Github (@effigies) when you start to add it.
>
> --
> Christopher J Markiewicz
> Ph.D. Candidate, Quantitative Neuroscience Laboratory
> Boston University
>
> _______________________________________________
> 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
>
--
Basile Pinsard
*PhD candidate, *
Laboratoire d'Imagerie Biomédicale, UMR S 1146 / UMR 7371, Sorbonne
Universités, UPMC, INSERM, CNRS
*Brain-Cognition-Behaviour Doctoral School **, *ED3C*, *UPMC, Sorbonne
Universités
Biomedical Sciences Doctoral School, Faculty of Medicine, Université de
Montréal
CRIUGM, Université de Montréal
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20160215/689c78ab/attachment-0001.html>
More information about the Pkg-ExpPsy-PyMVPA
mailing list