I know the general question about bias variance has been asked before. I understand the frequentist approach and the concept of model selection and the impact of bias and variance on "accuracy" of a prediction. I am looking for an intuitive explanation of bias and variance from a Bayesian perspective.
$\begingroup$
$\endgroup$
1
-
2$\begingroup$ Do you want an explanation along the same lines as here for Bayesian regression models, or are you looking for a discussion of bias and variance in sampling-theory regression models from a Bayesian perspective? Bias is automatically induced in the Bayesian approach just from using a prior, while the variance is decreased for the same reason. $\endgroup$– user44764Commented Jun 6, 2014 at 22:56
Add a comment
|