Gauge RR flooring issue#471
Conversation
JTPetter
commented
May 8, 2026
- fixes an issue where flooring at 0 after calculating indices lead to wrong results (https://support.jasp-services.com/JASP-Services/internal_issues/issues/19)
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #471 +/- ##
==========================================
- Coverage 84.96% 84.96% -0.01%
==========================================
Files 18 18
Lines 10012 10014 +2
==========================================
+ Hits 8507 8508 +1
- Misses 1505 1506 +1 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
There was a problem hiding this comment.
Pull request overview
Fixes Gauge r&R crossed-model variance component calculations when negative component estimates are floored to 0, ensuring reproducibility (reprod) is computed from the floored components rather than from pre-flooring values.
Changes:
- Recomputes
reprodafter applyingmax(0, ...)tooperatorand (when present)interaction. - Ensures
interactionis floored before contributing toreprodin the interaction case.
|
build builder bot build for glory |
✅ Build Complete!Your JASP module bundles have been successfully built for macOS (ARM) and Windows. 👉 Click here to download the artifacts (Scroll to the bottom of the page to find the "Artifacts" section). |
|
the issue is indeed fixed. however I was being stupid with some variable assignment and found a bug: |
juliuspfadt
left a comment
There was a problem hiding this comment.
see the error
also can you address the copilot feedback?
|
thanks, done! |
|
build builder bot build for glory |
✅ Build Complete!Your JASP module bundles have been successfully built for macOS (ARM) and Windows. 👉 Click here to download the artifacts (Scroll to the bottom of the page to find the "Artifacts" section). |
