kentman234 Wrote:
> - I want to go data-driven. That's why I mentioned
> ICA, to descriminate the components of the two
> classes i.e. one component should indicate a
> unique class. You said that this is not possible

I said I did not see how that could work - feel free to prove me wrong, that means I would have learnt something interesting.

Re your other questions:

> - I downloaded AFNI matlab toolbox. There are many
> files, which one to be used?

> I tried to download pyMVPA on my windows 7 but didn't work. I got an error message after installing this software. Is there any way to download and get the software work?

I would suggest you do a bit more homework before asking questions such as these, and if you ask them, please be sure you have used google and read the documentation. If you still cannot find a solution, it would be optimal if you are more precise about what exactly how want to achieve, what you have learnt from the documentation, what you have tried, what the output and error messages were (if applicable), why you think it did not work, and how your issue can be reproduced.

For example, the first question could be easily be answered if you googled for "afni read write brik". It would tell you that AFNI files are either generated from to3d or converted from other formats such as NIFTI or ANALYZE, and that the matlab functions for I/O are BrikLoad and WriteBrik. The second question could be due to many things, but without any more information it is unclear what steps to take. Also please note that this is a forum for AFNI users, so unless your pyMVPA issues are related to AFNI, it is better to ask questions on the pyMVPA mailing list.

A good read on how to ask questions in such a way that you are most likely to get constructive answers is here:

[www.catb.org]

Seriously, please *read* it.

Please note that my reply is not about being unwilling to help - but my time is limited, so I prefer to spend it on answering smart questions. Therefore, please consider the above suggestions and everybody will be happier.

best,
Nick