jacob-long / jacob-long/jtools

Diffrent ICC results between summ commend and sjPlot

Open
#159 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
R
Stars
171
Forks
23
PR merge metrics
No merged PRs in 30d

Description

I am running a MLM model using lmer with an additional level 1 variable.
The ICC I get using **summ** is very different than what I get using sjPlot (and also regular flowup ICC request after summary).

Why is that? Perhaps it takes into account not just the groups' random effect but also the added variable somehow?

I prefer to use the jtool summ results cause they are better for my aim, but not sure I can relay on it is because of the difference.

Contributor guide

Open the contributing guide

Research direction

Start by reproducing the MLM example with lmer, then compare the ICC from summ with sjPlot and the post-summary ICC request. Determine why the results differ and clarify or correct the behavior so users can tell which result is reliable.

Written by the indexing model from the issue text.

Assessment

Tech stack
r
Domain
analytics
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.