Toni
2013-07-08
I have a data similar to Foti, Hajcak and Dien (2009) with 3 conditions, positive, neutral and negative pictures. Now I want to export the factor scores after a PCA with 10 temporal factors and 3 spatial factors in order to perform an ANOVA similar in the mentioned paper. I thought that these data should be in EPdata.pca.FacScrST, but this matrix is numberOfSubjects x 30, assuming that 30 are the scores of all the temporospatial factors, but, where can I find the factor scores for all temporospatial factors and for the 3 conditions (positive, neutral and negative images)?
I know that is better to export the voltage reconstructed data with the window function, but selecting diffentes electrodes for each of the 30 factors is causing me reluctances, what do you think?
Cheers!!
Toni
Joe Dien
2013-07-08
Hi Toni,
are you sure about that? The rows of EPdata.pca.FacScrST should indeed be numberOfSubjects*numberOfConditions as documented in the doPCAST.m file. I just ran a test PCA and it was fine. By the way, you don't need to go mucking around in the ept file for the factor score info. Just window the PCA file that the EP Toolkit generates for you. It is equivalent to the factor scores and will give you the same ANOVA results, but has been rescaled to microvolts for maximum interpretability. See Dien & Frishkoff (2005) for a tutorial on the subject.
Joe
On Jul 8, 2013, at 4:03 AM, Toni tonivo5@users.sf.net wrote:
I have a data similar to Foti, Hajcak and Dien (2009) with 3 conditions, positive, neutral and negative pictures. Now I want to export the factor scores after a PCA with 10 temporal factors and 3 spatial factors in order to perform an ANOVA similar in the mentioned paper. I thought that these data should be in EPdata.pca.FacScrST, but this matrix is numberOfSubjects x 30, assuming that 30 are the scores of all the temporospatial factors, but, where can I find the factor scores for all temporospatial factors and for the 3 conditions (positive, neutral and negative images)?
Cheers,
Toni
Factor Scores for different cells
Sent from sourceforge.net because you indicated interest in https://sourceforge.net/p/erppcatoolkit/discussion/767176/
To unsubscribe from further messages, please visit https://sourceforge.net/auth/subscriptions/
Joseph Dien,
Senior Research Scientist
University of Maryland
E-mail: jdien07@mac.com
Phone: 301-226-8848
Fax: 301-226-8811
http://joedien.com//
Toni
2013-07-08
Sorry, my bad. The data is exactly how you describe.
Cheers
Joe Dien
2013-07-09
no prob! :)
On Jul 8, 2013, at 6:16 PM, Toni tonivo5@users.sf.net wrote:
Sorry, my bad. The data is exactly how you describe.
Cheers
Factor Scores for different cells
Sent from sourceforge.net because you indicated interest in https://sourceforge.net/p/erppcatoolkit/discussion/767176/
To unsubscribe from further messages, please visit https://sourceforge.net/auth/subscriptions/
Joseph Dien,
Senior Research Scientist
University of Maryland
E-mail: jdien07@mac.com
Phone: 301-226-8848
Fax: 301-226-8811
http://joedien.com//