JASP Version

0.19.3

Commit ID

No response

JASP Module

Process

What analysis are you seeing the problem on?

Parameter estimates for 'direct and indirect effects' and 'total effects'

What OS are you seeing the problem on?

Windows 11

Bug Description

I have explained some bugs in the ppt file attached and the related .jasp file I used.

JASP_Process.pptx

lmx_model21.zip

In the third line of the results of direct and indirect results, when the value of POS is 50 percentile and the value of LMX is 16 percentile, the label describes it as (a1 ＋ a3 ✻ 0.485) ✻ (b1 ＋ c3 ✻ 0.161) and the estimate is 0.394. However, 16 percentile of LMX is not 0.161, but -1.964 as shown in the second line of the results. Thus, the estimate result should be (a1 ＋ a3 ✻ 0.485) ✻ (b1 ＋ c3 ✻ -1.964) ≈ 0.189.

In the fourth line of the results of direct and indirect results, when the value of POS is 84 percentile and the value of LMX is 16 percentile, the label describes it as (a1 ＋ a3 ✻ 1.485) ✻ (b1 ＋ c3 ✻ 1.973) and the estimate is 0.613. However, 16 percentile of LMX is not 1.973, but -1.964 as shown in the second line of the results. Thus, the estimate result should be (a1 ＋ a3 ✻ 1.485) ✻ (b1 ＋ c3 ✻ -1.964) ≈ 0.204.

Expected Behaviour

These mismatches between the conditions of moderate variables (16, 50, 84 percentiles) and the estimates are founded and repeated in all the estimates for direct, indirect and total results. In other words, when the two moderate variables with three values (16, 50, 84 percentiles) are in a mediation path, nine different estimate results should be reported. However, the results repeated three different results.

Steps to Reproduce

These bugs are always shown whenever I used the Process module.

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.