If I have multiple outcomes -- different variables being measured for each subject -- and I believe that the variables are correlated, how do I adjust the power calculation? For example, say I'm measuring (somehow)"monthly income" and "food insecurity" and "financial resilience"? Or "self-rated health" and "number of chronic conditions" and "number of different prescription medications"? Do I just pick one outcome, or should I adjust somehow? Is there a good (accessible) reference?
S. Béatrice Marianne Ewalds-Kvist
Do a standard multiple regression analysis and read the Tolerance and VIF-values
VIF = variance inflated factor. Its value must be > .10 in contrast to the tolerance value that must be less than .10. If this is not the case, multicollinearity is at hand.
0 votes
0 thanks
- Badges
- Science topic
- Similar topics
- Medicine
- Epi
- Age Groups
- Children
More Evelyn L Forget's questions See All
Similar questions and discussions