Incorporating meta-analysis data into bayesian correlation analysis in JASP
Hi everyone,
I'm currently working on a project that requires me to perform a bayesian correlation analysis using two questionnaires. In my research, I encountered a meta-analysis reporting a mean correlation (r) of 0.31. This meta-analysis not only used the same questionnaires, but also analyzed a comparable sample.
I want to use the results of this meta-analysis to inform the priors in my bayesian analysis. However, I'm uncertain about the method to incorporate this data as an informed prior in JASP. Any advice or resources on this would be greatly appreciated!
Kind regards,
Paul
Comments
Hi Paul,
The prior that JASP allows is centered on a value of rho=0. Now you could do a one-sided test (allowing only positive correlations; this might be implied by the theory), and you can change the prior width. However, you cannot presently center the prior on a non-zero value of rho. This would be a good feature request.
Cheers,
E.J.