<html><head></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; color: rgb(0, 0, 0); font-size: 14px; font-family: Calibri, sans-serif; "><div><div><div><div style="font-family: Consolas; font-size: medium; ">Hello John,</div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">I have given this alot of thought in the past, and there are a few things that might be worth trying:</div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">1. When you say that the behavioral trait is not the same "type" as the features, do you mean that it is not ordinal? If it is ordinal, then I don't see any problem with adding it as a feature. Indeed this is how a lot of data fusion algorithms work. You should be careful that the variance of the behavioral score matches the variance of the other features. I.E. you should z-score it as well as the features. This will ensure that the resulting feature weights are comparable. </div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">2. You could regress out the behavior score from your feature space. Fit a glm to each voxel with the behavioral score as the regressor of interest, and then perform the MVPA analysis on the residuals.</div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">3. You could perform a MVPA regression to the behavioral score, perform a feature selection to find the features most predictive of the behavioral score, and then remove those features from the for the A vs. B classification.</div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">4. How predictive is the behavioral trait of the group membership? Can you just threshold the behavioral score to ascertain group membership? If so then you could perform a MVPA regression to the behavioral score, apply a threshold to the prediction output, and see if this performs better to classify group membership than a classifier trained using class membership as the labels. I think that this is a pretty interesting idea.</div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">Just a few thoughts.</div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">Cheers,</div><div style="font-family: Consolas; font-size: medium; ">Cameron</div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">Hi Jo -</div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">Thanks for your response. The features are structural data, so yes, they are</div><div style="font-family: Consolas; font-size: medium; ">voxel values.</div><div style="font-family: Consolas; font-size: medium; ">It just so happens that a behavioral trait is also predictive of whether or</div><div style="font-family: Consolas; font-size: medium; ">not participants are in Group A or Group B. Since the behavioral trait is</div><div style="font-family: Consolas; font-size: medium; ">not of the same "type" as the features, it seems incorrect to simply add it</div><div style="font-family: Consolas; font-size: medium; ">to the feature space. Still, though, I would like to "control" for the</div><div style="font-family: Consolas; font-size: medium; ">predictability of that trait in the MVPA.</div><div style="font-family: Consolas; font-size: medium; ">Does that make more sense?</div><div style="font-family: Consolas; font-size: medium; "><br></div><div style="font-family: Consolas; font-size: medium; ">Cheers,</div><div style="font-family: Consolas; font-size: medium; ">John</div></div><div><div><div>---</div><div><div style="font-family: Consolas, monospace; font-size: 12px; ">R. Cameron Craddock, PhD</div><div style="font-family: Consolas, monospace; font-size: 12px; ">Postdoctoral Fellow</div><div style="font-family: Consolas, monospace; font-size: 12px; ">Virginia Tech Carilion Research Institute</div><div style="font-family: Consolas, monospace; font-size: 12px; ">Roanoke VA</div><div style="font-family: Consolas, monospace; font-size: 12px; "><br></div><div style="font-family: Consolas, monospace; font-size: 12px; ">404-625-4973</div><div style="font-family: Consolas, monospace; font-size: 12px; ">cameron.craddock@vt.edu</div></div></div></div></div></div></body></html>