[Bug]: Bayesian rmANCOVA post-hoc tests all show the same values

[kwellstein]

JASP Version

0.95.1

Commit ID

No response

JASP Module

ANOVA

What analysis are you seeing the problem on?

post-hoc tests of Bayesian rmANCOVA

What OS are you seeing the problem on?

macOS Intel

Bug Description

I conducted a Bayesian rmANCOVA that showed evidence for the interaction vs. the main effect and null model.
See the data and jasp analysis attached:

VAGUS_RQ03_dataTable.csv.zip

VAGUS_RQ03_dataTable_bugReport.jasp.zip

Expected Behaviour

I would have expected to see different values for each post-hoc test...

Steps to Reproduce

see jasp file...

Log (if any)

No response

More Debug Information

No response

Final Checklist

• I have included a screenshot showcasing the issue, if possible.
• I have included a JASP file (zipped) or data file that causes the crash/bug, if applicable.
• I have accurately described the bug, and steps to reproduce it.

[JohnnyDoorn]

Hi @kwellstein,

Thank you for your report. I looked at your .jasp file and looked at the descriptives - it seems that the group means are the same for the repeated measures columns:

Because of the identical means and sd's of painCalib/calib, and simpleDown/simpleUp; some numeric results are not defined (calib vs paincalib, for instance) in the posthoc table; while others are identical. So maybe something went wrong in the data wrangling?

Cheers
Johnny

[kwellstein]

Oh no, I apologize for not spotting this earlier. Consider the issue closed.