0
$\begingroup$

I have the following situation and am hoping that someone can point me in the right direction. I am completing an experiment under 2 conditions (1 and 2) and measuring 2 variables (A and B). I am interested in how variable B changes between the 2 conditions. However there is reason to believe that Variables A and B are correlated. In my data the relationship between the two looks something like this:

enter image description here

If I plot the histograms of values for variables A and B I get something that looks like the following:

enter image description here

I am interested in how the mean and variance of Variable B changes in response to the difference in experimental conditions in a way that is independent of variable A. What would be the proper way to determine this?

For instance would it be correct to resample my data so that both samples used to compute differences in the distribution of B come from the same distribution of values for Variable A?

Thank you

$\endgroup$
0
$\begingroup$

I suppose you could enter variable A as a covariate, but what you are describing is a pretty clear cut example of an interaction. The effect of condition (1 vs 2) on B is dependent on the level of condition A. The 'by-the-book' answer is thus that the interaction must be interpreted. 'What is the effect of condition on B' doesn't have a clear answer otherwise (it's 0 at low A, and large at high A)

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.