easystats / easystats/performance

Comparing frequentist and Bayesian models

Open
#738 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

3 investigators :grey_question::question:
Dominant language
R
Stars
1.2k
Forks
109
Avg merge
6h 34m
Merged PRs (30d)
8

Description

Is it possible to compare a Bayesian and frequentist model in a meaningful way? I tried compare_performance() for comparing the same model specified with brm and glmmTMB, but the error suggests to me that it might not be possible (or meaningful). Error is:

> performance::compare_performance(
+   mod_ratio_state, 
+   bayes_ratio_state)
Error in loo::stacking_weights(lpd_point) : 
  At least two models are required for stacking weights.

(I'm trying to make a case for using Variance Ratio over ICC, and am trying to pre-empt questions about the model fits).

Might relate to https://github.com/easystats/performance/issues/716.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with performance::compare_performance() and reproduce the example using the brm and glmmTMB models. Inspect the loo::stacking_weights error and the related issue #716. Done means establishing whether cross-framework comparison is supported and defining the expected behavior or documentation for this case.

Written by the indexing model from the issue text.

Assessment

Tech stack
r
Domain
analytics, data
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.