Tests of normalities

Everything related to development of the jamovi platform

by jonathon » Mon Sep 23, 2019 12:11 am

hi,

if you have your p-value settings set to 'significant figures', then small values will be represented with scientific notation (https://en.wikipedia.org/wiki/Scientifi ... E-notation). you change these to 'decimal places' if you prefer the < .001.

cheers

jonathon
User avatar
jonathon
 
Posts: 1474
Joined: Fri Jan 27, 2017 10:04 am

by MAgojam » Mon Sep 23, 2019 8:30 am

pullume wrote:However im getting something totally different for my assignment analysis.
I get these results with e's in them - 6.720e-7 and 1.722e-4 . Can you explain these please?


Hi, pullume.
Your p values, to make them more readable, are reported as "Scientific notation", which reduces the number of zero decimals to be displayed.
Your values ...
without e-7 they would be
0.000000672
without e-4 they would be
0.0001722

Cheer.
Maurizio
User avatar
MAgojam
 
Posts: 116
Joined: Thu Jun 08, 2017 2:33 pm
Location: Parma (Italy)

by pullume » Mon Sep 23, 2019 12:44 pm

MAgojam wrote:
pullume wrote:However im getting something totally different for my assignment analysis.
I get these results with e's in them - 6.720e-7 and 1.722e-4 . Can you explain these please?


Hi, pullume.
Your p values, to make them more readable, are reported as "Scientific notation", which reduces the number of zero decimals to be displayed.
Your values ...
without e-7 they would be
0.000000672
without e-4 they would be
0.0001722

Cheer.
Maurizio


:-D Dear Maurizio,

I can't thank you enough!

xxx
pullume
 
Posts: 2
Joined: Wed Sep 18, 2019 2:14 pm

by Wake » Wed Jan 22, 2020 2:46 pm

jonathon wrote:hi,

moretests is what we call an "addon", where it adds results to existing analyses. just run the t-test or ANOVA as usual, and choose 'normality tests' (granted, there's an issue with 'normality tests' still be labeled as shapiro-wilk). see here:

cheers

jonathon


I've just tried this on jamovi 1.2.2 and asking for Shapiro-Wilk in Linear Regression doesn't give the K-S test, whereas it does in Independent Samples T-Test

Cheers,

Wake
Wake
 
Posts: 37
Joined: Tue Jun 26, 2018 8:31 am

by LDartnell » Wed Jul 29, 2020 3:51 am

Wake wrote:
jonathon wrote:hi,

moretests is what we call an "addon", where it adds results to existing analyses. just run the t-test or ANOVA as usual, and choose 'normality tests' (granted, there's an issue with 'normality tests' still be labeled as shapiro-wilk). see here:

cheers

jonathon


I've just tried this on jamovi 1.2.2 and asking for Shapiro-Wilk in Linear Regression doesn't give the K-S test, whereas it does in Independent Samples T-Test

Cheers,

Wake


Hey there, wondering if you'd consider also adding the normality tests S-W and K-S to the Descriptives and Repeated Measures ANOVA (I'm using the latter for a Mixed/Factorial ANOVA)?

Thanks
Loraine
LDartnell
 
Posts: 1
Joined: Wed Jul 29, 2020 3:05 am

by jonathon » Wed Jul 29, 2020 3:53 am

yeah, i'd love to, but haven't had the time to yet, sorry.

will hopefully get to it in the next few weeks.

cheers
User avatar
jonathon
 
Posts: 1474
Joined: Fri Jan 27, 2017 10:04 am

by Asmaryadi » Fri Aug 14, 2020 4:01 pm

I found different result of Shapiro-W when tested in descriptive option and in independent t test option. It made me confused.
Asmaryadi
 
Posts: 3
Joined: Wed Jun 24, 2020 12:32 pm

Previous

Return to jamovi development