Bayesian Partial Correlation
Hello everyone,
For my study, I would need to do partial correlation between 6 variables, controlling for another 3. I would like to report the Bayesian alternative, but I know JASP do not offer yet partial correlations. I know about the BayesMed package in R, which do offer BF for partial correlations (there are couple more option floating around), but only between 2 variable, controlling for 1. So my questions are 1) is it possible (and how) to adjust the BayesMed partial correlation in a way it can handle more variables? (it might be a bit of stupid question, but I have just basic knowledge in R, and I am not sure how this should be done), and 2) if the first is not possible, is reporting the BFs from multiple linear regressions a valid workaround? (I have seen contradicting opinions about this)
Thank you in advance,
Mila
Comments
Hi Mila,
I don't think (1) is an option, and I'm not sure about (2). There are some Bayesian network models you could check out. I believe there is some recent work by Joris Mulder (Tilburg Uni) that may be relevant here.
Cheers,
E.J.
Many thanks for the response!
Best,
Mila