Non-parametric test with confounding factors (many covariates)

#1
First, sorry for my English, if I'm not clear enough, tell me!
In my project, I have many variables but a very small sample (non-parametric). I'm trying to prove a link between two variables while correcting for covariates. In short, we are looking at white matter tracts and their links to visuospatial function and quality of life (QoL). We are analyzing 3 tracts, which can either be normal, displaced or ruptured (ordinal) and we have 8 scores for visuospatial abilities. Let's define variables:
  • Y1 = tract 1 integrity (3 categories)
  • Y2 = tract 2 integrity (3 categories)
  • Y3 = tract 3 integrity (3 categories)
  • X1 to X8 = visuospatial test scores (quantitative discret)
Others:
  • X9 = QoL score (quantitative discrete)
  • X10 ... = age, gender, etc. (these covariates are not important for right now, I'll had them in my study latter)
The thing is that while we are looking the links between the integrity of the first tract and the visuospatial function (Y1 and X1-X9) for example, there is a possibility that the second tract (Y2 and/or Y3) is also affected and thus, Y2 might be the one responsible of the deficit and not Y1 (I need to correct for Y2 and Y3 to prove that Y1 is responsible alone). I was thinking of logistic regression, but I'm not sure how to treat Y2 and Y3.
There is a second part to the project!! Each patient undergo a surgery and we want to compare if the change in the integrity of the tract (Y) correlates with the change in visuospatial capabilities (X) pre and post surgery (so if a white matter tract is repaired, does visuospatial function return and conversely, if we disrupt a tract in surgery, does the visuospatial function decrease?). So it's like a repeated mesures (2 times), but I still have the same issue with Y2 and Y3 vs Y1 (if Y1 is repaired, but Y2 is not and Y3 is ruptured during surgery for example)... I was thinking about a generalized estimating equation (mixed model), but still not sure how to treat my variables.

Do you know which test to use? My independent variable is the integrity of the tract, but how do I treat the other tracts when looking at only one?

Thanks for your help!
 

katxt

Active Member
#2
Your English is very clear, sdamour.
Your statistical problem is a hard one. Your research looks serious and important with potentially life changing results . There is probably no general advice this forum can give you that will enable you, personally, to analyze your data as effectively as it deserves. You are a physiologist and not expected to also be a statistician. You need a statistician on your team, either as a paid consultant or as a collaborator. I hope it all works out. kat
 
#3
Your English is very clear, sdamour.
Your statistical problem is a hard one. Your research looks serious and important with potentially life changing results . There is probably no general advice this forum can give you that will enable you, personally, to analyze your data as effectively as it deserves. You are a physiologist and not expected to also be a statistician. You need a statistician on your team, either as a paid consultant or as a collaborator. I hope it all works out. kat
Thanks! I contacted a statistician but I was not entirely convinced by his choice! I did physics before health science, so I'm a bit familiar with statistics, but for my problem, it is quite hard to find the right test... Thank you for your answer, I'll contact another statistician :)