JISCMail - FSL Archives

Hi Sam,

I can't find the original thread using just this number. Could you send the permalink (shown at the bottom of the messages on Jiscmail)?

Could you also show the plot you've made?

At any rate, it seems the plot is for the interaction, so in fact, the groups may have no significant association with GM, but when this (presumably weak) association is compared between groups, it becomes significant. You'd have to make two scatter plots, one for each of the two groups represented in the contrast. They may show opposite trends (most likely from the description), or at least different slopes. Also, this plot needs to use data from voxels or regions where the interaction was found significant. Finally, a it seems there is a 7th EV for some other nuisance, and that needs to be taken into account too.

All the best,

Anderson

On 16 November 2015 at 16:12, Sam Rogers <[log in to unmask]');" target="_blank">[log in to unmask]> wrote:

Hi Anderson,

You have kindly provided advice in the past regarding this design (#070672), where I have 3 groups and a measure of IQ for each of these. I have run this analysis in the way you recommend, where EVs 1-3 are for group and 4-6 are for the IQ measure. I ran the interactions and some of these are significant. I wanted to plot these to have a look at the interactions, but I am confused that neither plot shows a correlation with gray matter. For C1 as you suggest in our earlier discussion [0 0 0 1 -1 0 0] I anticipated experimental group 1 to show a correlation with gray matter in the significant voxels, and group 2 to show no correlation (or a correlation in the opposite direction). Both plots actually show no linear relationship between the gray matter and the IQ. Have I misunderstood the meaning of the contrast here?

Thanks for advising.
Sam.