Hi Dr. Nonald Mclaren,
Could I ask a related question?
I have 11 subjects and every subject had 3 runs /sessions with different stimuli. Maybe I should say same stimuli ( all are auditory stimuli), just different levels ( only emotion levels are different in 3 runs).
I are trying to get the main effects no matter the emotion levels and use the subjects as 1 factor ( independent, unequal variance) , second factor as task ( not independent, equal variance, 3 levels).
IS that appropriate? IF so, should the degree of freedom be 27? Does that make sense?
thanks for your time,
Xiaoying
________________________________________
From: SPM (Statistical Parametric Mapping) [[log in to unmask]] on behalf of MCLAREN, Donald [[log in to unmask]]
Sent: Monday, April 02, 2012 1:43 PM
To: [log in to unmask]
Subject: Re: [SPM] Flex.Factorial - Factor matrix question
See inline responses below.
On Mon, Apr 2, 2012 at 4:08 AM, Kavita Vemuri <[log in to unmask]<mailto:[log in to unmask]>> wrote:
Hi
I am trying flexible factorial (within subject), where I have 1 subject group of 15 subjects and 3 tasks.
I input the following
First factor as 'subject'
Independence 'yes'
Variance 'equal'
Second factor as 'task'
Independence 'no'
variance ' unequal'
variance should be set to equal.
Specify all
Scans : contrast images for all 15 subjects and all the three tasks.
I am bit confused on the Factor Matrix, the help at the bottom says ' nscan X 4 matrix'. How do I design the Factor matrix.
Column 1 - 1s
Column 2 - level of factor 1
Column 3 - level of factor 2 (or 1s, if only 1 factor)
Column 4 - level of factor 3 (or 1s, if only 2 factors)
There wil be N*C rows, where N is the number of subjects and C is the number of conditions. Each row has the levels of the scan entered for that row.
In the main factor, I take factor '1'.
You will need two main effects. One for factor 1 and one for factor 2. Both are needed for a repeated measures analysis.
Please help.
Kavita
The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.
|