/sci/ - Science & Math

>>15214043
I'm a statisticslet, and uneducated on top of that. I don't know what is correct to do.

I have 4 treatments and in each there's an individual, and for each there's a set of metrics (dozen gene expressions, behavior, anatomical measurements). I took everything and correlations are weak but make sense. But if I break them down by treatments the matrix changes. Those changes are probably valuable and have information in them.

I'm pretty sure the operation is in part of some multidimensional workflow and has a proper scientific name, but I don't know the name so I can't google it and go from there.