Task PLS with CI - part 2
mkim
Posted on 11/03/09 16:27:49
Number of posts: 34
Hi.
I ran a Task PLS analysis (with CI) and am trying to re-create the LV profiles in Excel. I have 2 groups with 18 subjects in Group1 and 13 subjects in Group2, and there are 6 conditions. The analysis gave me 12 LV's. I extracted the Brain Score values (b_score) and got 12 columns (for the 12 LV's, I think) and the 186 rows of brain scores represent the number of subjects per condition per group (I think):
LV1 (for example)
18 condition1
18 condition2
18 condition3
18 condition4
18 condition5
18 condition6
13 condition1
13 condition2
13 condition3
13 condition4
13 condition5
13 condition6
Is that correct? I averaged the brain score values for each condition but only the Group1 averages matched the Brain Score LV profile......did I miss something? Thanks once again for you help!
Miyoung
Untitled Post
I'm Online
jshen
Posted on 11/03/09 16:48:34
Number of posts: 291
The rows that you mentioned are correct. It's always subject in condition in group.
Brain score in plot "Task PLS with CI" is not just the average of brain score values for each condition, because the 'datamat' here in the calculation should also be mean-centered.. i.e.:
Rather than: task_mean( datamat * brainlv )
It is: task_mean( mean_center( datamat) * brainlv )
That's why I told you to re-run the analysis.
If you still cannot match the numbers, please upload your datamats and result file onto your FTP server, and post the URL here. So I will look into it.
Untitled Post
mkim
Posted on 11/03/09 17:36:20
Number of posts: 34
Hi, Jimmy.
Maybe it was just a coincidence that the average b_scores matched the Brain Scores in Group1?..... Is there a quick and easy way to obtain the values on the Brain Scores Plot - I just need to represent the graph in Excel (with CI's and all)? Thanks once again Jimmy!
Miyoung
Untitled Post
I'm Online
nlobaugh
Posted on 11/03/09 17:43:14
Number of posts: 229
miyoung...
you will need to use matlab, or a smarter plotting package to plot the CI's.
Excel is expecting symmetric values for error bars, which is not what we provide with the CI.
nancy
Untitled Post
mkim
Posted on 11/03/09 17:54:43
Number of posts: 34
Hi, Nancy.
Thanks for your reply - I used Matlab to obtain the b_scores values and the upper/lower limits of the CI I see on the one of the LV's PLS Brain Score Plot. I want to obtain the values for each condition for each group (a total of 12 bars, since I have 2 groups and 6 conditions) that I see on this plot - I thought that averaging the b_score values of the subjects in each condition in each group would help me obtain them but it seems a lot more complex than simply doing so (per Jimmy's reply to my initial post on this thread). I already obtained the upper/lower limits of the CI (per Jimmy's suggestion on an earlier post - by using "boot_result.ulusc" and "boot_result.llusc") - is there a way to get the values I see on the Plot without having to do apply complex computation? Thanks once again for your help!!
Miyoung
Untitled Post
as22kk
Posted on 11/04/09 10:47:32
Number of posts: 60
If you sought the values of brain score on brain scrore with CI plot, you can simply find them on boot-result.orig_usc.The ulusc and llusc are the uper and lower range of the confidance interval.If you have a skew data, which makes the bars non-symmetric, than you can use the adjusted one ulusc_adj and llusc_adj!
/Alireza