Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Multiple comparisons adjustments, null control etc. in bayestestR #485

Open
DominiqueMakowski opened this issue Nov 6, 2021 · 5 comments
Labels
Feature idea 🔥 New feature or request

Comments

@DominiqueMakowski
Copy link
Member

In the debate whether yes or no Bayesian analyses could/should be "corrected" for multiple testing, comparisons and false positives, this suggests extending the null control method (implemented in JASP):

Null_Control_Jong.pdf

It would be nice to make something like that available in bayestestR

Could interest @mattansb

@DominiqueMakowski DominiqueMakowski added the Feature idea 🔥 New feature or request label Nov 6, 2021
@mattansb
Copy link
Member

mattansb commented Nov 7, 2021

These "adjustments" are for the prior odds between pairs/sets of hypotheses (not for any of the measures of evidence).
How would you like to see these implemented?

(Personally not a fan of these "let me tell you what your priors are" tools 😅)

@mattansb
Copy link
Member

I don't think this is an avenue worth perusing (see previous comment about defining others' priors).

But if you are interested in such methods of default priors, you might also want to take a look at the BAS package, which computes term-wise adjusted priors.

@strengejacke
Copy link
Member

(Personally not a fan of these "let me tell you what your priors are" tools 😅)

image

@bwiernik
Copy link
Contributor

We do also have curve-wise intervals, so that is one method for multiple testing adjustment

@mattansb
Copy link
Member

Yup, I'm def more in favor of those.
(The ones discussed here are for independent tests, or pairwise model-less tests...)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Feature idea 🔥 New feature or request
Projects
None yet
Development

No branches or pull requests

4 participants