Bayesian Correlations are unaffected by the prior
Playing with the prior in the Bayesian Correlation Matrix changes the Bayes factors, but does not change the estimated correlation. Why is this? If the estimate is based on the posterior, shouldn't changes to the prior change the estimate?
Comments
Same r, different BF
Hi MSB,
"r" is the sample value. The underlying model parameter is "rho".
Cheers,
E.J.