Open Alejandro-84 opened 1 year ago
Agreed, would be good to have!
@Alejandro-84 There is a project in development improving the functionality of raincloud plots. Since we have a raincloud difference plot lets press thumbs that this will then be customizable to show mean and CI!
@Alejandro-84 The new raincloud plot module is now live within descriptives in 0.19 beta. To test yourself you could get the latest beta from here: https://static.jasp-stats.org/Nightlies/
However it does not yet include the possibility to use mulitple column data in one plot, which is commonly used for multiple time steps. Thus you would still need to compute differences manualy. We can still hope that your feature request to include the difference CI plot directly into the t-Test module makes it into the next release.
Also I just realized, that the "rest" of this issue is now basically a duplicate of https://github.com/jasp-stats/jasp-issues/issues/33
If we have a button that enables seemless switching between wide and long format data we do not need to add special-long/wide-data-format plotting options for all the different plots out there. So lets just implement "that button" and thus tackle all sorts of plots at the same time.
Description
The paired-samples t-test is often accompanied by a graph with the mean difference and confidence intervals to depict whether the differences did statistically significantly differ from zero. However, JASP (v 0.16.4) does not include this feature in the T-Tests -> Paired Samples T-Test module. Instead, it allows for descriptive and bar graphs which do not necessarily convey the info regarding a mean difference being different from zero.
Purpose
To include a graphic representation of paired-samples t-test results.
Use-case
No response
Is your feature request related to a problem?
No response
Is your feature request related to a JASP module?
T-Tests
Describe the solution you would like
Adding the option to make a graph with the mean difference and the confidence intervals (with the possibility of modifying the intervals), information that is already reported in the paired-samples t-test output tables.
Describe alternatives that you have considered
It is possible to make a graph like that in JASP with a different method. First, calculating the differences between the paired samples for each participant (or case) in the data viewer. Next, select the "One Sample T-Test" in the "T-Tests" tab. Move the calculated differences right to the variables box, and select the descriptives or bar plots. However, this method is less intuitive than including the option in the paired samples t-test module.
Additional context
No response