Summary Statistics Bayesian Independent Samples T-Test: Labels in prior and posterior plots switch upon changing from BF10 to BF01, while they shouldn't

[Diesfeldt]

• JASP version: 0.12.1
• OS name and version:
• Analysis:
• Bug description:
• Expected behaviour:

Steps to reproduce:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

[boutinb]

@Diesfeldt Can you be a bit more descriptive about the issue?

[Diesfeldt]

Hi Bruno,

Thanks. I uploaded a text file which contains my question. See enclosed.

Hope to hear your response.

Best,

Han Diesfeldt

Verzonden vanuit Mailhttps://go.microsoft.com/fwlink/?LinkId=550986 voor Windows 10

Van: bruno boutinmailto:notifications@github.com Verzonden: maandag 8 juni 2020 10:40 Aan: jasp-stats/jasp-issuesmailto:jasp-issues@noreply.github.com CC: Diesfeldtmailto:h.diesfeldt@outlook.com; Mentionmailto:mention@noreply.github.com Onderwerp: Re: [jasp-stats/jasp-issues] Summary Statistics Bayesian Independent Samples T-Test (#796)

@Diesfeldthttps://github.com/Diesfeldt Can you be a bit more descriptive about the issue?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHubhttps://github.com/jasp-stats/jasp-issues/issues/796#issuecomment-640457974, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AKXOHB3RHNWNEBH5SBIFOQTRVSPWRANCNFSM4NWBSFNQ.

[boutinb]

The file was apparently not correctly uploaded in GitHub. Can you try again? You have to do that from the GitHub site. If GitHub refuse to load your file, you can first zip the file.

[AlexanderLyNL]

Alternatively, you can also copy paste the content of the text file into the comment box. Furthermore, if it concerns a bug or feature request, it would be good to provide us with the requested information as displayed in the issue template, so we have enough information to handle the problem, see also our guideline here:

https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/

[Diesfeldt]

Hi Alexander,

Thanks very much. This is my remark or question: JASP version 0.12.1 Input: t=2.166 n1 = 49 n2 = 536 If BF10 has been activated the plot says BF10 = 1.427, as in the Table. However, when activating BF01, the Table correctly displays BF01 = 0.701, but the plot says BF10 = 0.701. The pizza plot accordingly does not correctly display data|H1 and data|H0.

I can send you a copy of the JASP output by email. This comment box does not accept the JASP output results.

Best,

Han

[AlexanderLyNL]

Hi Han,

Thanks for the report. It seems that the summary stats plots were implemented before a plot update and acts a bit too flexible now. @ASarafoglou would you like to have a look at this?

Expected behaviour

• The plot should not switch labels if BF10 or BF01 is chosen.
• This seems to occur in all three versions of t-tests in the summary stats module. I have not checked whether this occurs in the other summary stats analyses.

JASP file https://www.dropbox.com/s/9l1lchiixuenly7/labelSwitchingInSSTTestPlots.jasp?dl=0

Cheers, Alexander

[Diesfeldt]

Thanks very much, Alexander. I hope my remark is helpful. Thanks also for introducing me to JASP a few years ago.

Best,

Han

[AlexanderLyNL]

Hi Han,

This is very helpful for us. Despite many testing rounds before releasing a new version some issues remain. It's thanks to user reports that the remaining issues get removed. I hope you enjoy JASP, and feel free to request any missing features. Thanks again for reporting the bug.

Cheers, Alexander

[ASarafoglou]

I do not think that I can fix this issue before the next release, without having the JASP programmers around to help me out (I haven't coded for JASP since December). I would be thankful if the task would get allocated to somebody else, who can probably fix this issue in 20 minutes.

[akashrajkn]

I'll take this issue

[Diesfeldt]

Thank you very much.

Best,

Han Diesfeldt

Verzonden vanuit Mailhttps://go.microsoft.com/fwlink/?LinkId=550986 voor Windows 10

Van: akash rajmailto:notifications@github.com Verzonden: maandag 13 juli 2020 10:25 Aan: jasp-stats/jasp-issuesmailto:jasp-issues@noreply.github.com CC: Diesfeldtmailto:h.diesfeldt@outlook.com; Mentionmailto:mention@noreply.github.com Onderwerp: Re: [jasp-stats/jasp-issues] Summary Statistics Bayesian Independent Samples T-Test: Labels in prior and posterior plots switch upon changing from BF10 to BF01, while they shouldn't (#796)

I'll take this issue

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHubhttps://github.com/jasp-stats/jasp-issues/issues/796#issuecomment-657403893, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AKXOHB6Q5Q6VGW3NX6MZKO3R3LAHFANCNFSM4NWBSFNQ.