A Bayesian multilevel model with an informative prior is a penalized meta-regression for free. :)
Has anyone developed penalized meta-regression methods? Meta-regression is usually high p/n, so I expect much overfitting.
-
-
-
Yes, but I don't like Bayesian methods that much. Too much work to use.
-
Well, you can wait & hope someone writes specialcase ML algo sans any dealbreakers for all your problem. Or can learn JAGS.
-
I already know JAGS, I just don't use it. IMO, in most (not all) cases B methods are complicated, time consuming and unnecessary.
-
If you're asking, this is obviously one of those cases. And the more advanced your needs, the more often it'll happen...
-
isn't brms the better move here?
-
Mayb if you're willing to use Stan. Bit worried about immaturity - isn't it still missing stuff like discrete vars?
- 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.