Differences in Shapiro-Wilk P.value with ANOVA

General help and assistance with jamovi. Bug reports can be made at our issues page: https://github.com/jamovi/jamovi/issues . (If you're unsure feel free to discuss it here)
Post Reply
IrenevW
Posts: 1
Joined: Tue Oct 04, 2022 6:51 pm

Differences in Shapiro-Wilk P.value with ANOVA

Post by IrenevW »

Depending on whether the "One-way ANOVA" or "ANOVA" is run, the Shapiro-Wilk P.value changes. The Shapiro-Wilk P.value from the the "One-way ANOVA" was 0.807, while the Shapiro-Wilk P.value from the "ANOVA" was 0.817. I cannot work out why the difference is occurring - what is the difference in coding for these two Shapiro-Wilks?
User avatar
jonathon
Posts: 2613
Joined: Fri Jan 27, 2017 10:04 am

Re: Differences in Shapiro-Wilk P.value with ANOVA

Post by jonathon »

hi, you'd need to provide a .omv file before we could comment (you may need to zip it up first).

cheers

jonathon
MOPOLV
Posts: 2
Joined: Mon Aug 14, 2023 7:00 am

Re: Differences in Shapiro-Wilk P.value with ANOVA

Post by MOPOLV »

Good Morning,

I have the same problem, I have obtained different shapiro-wilk pvalues in anova one-way and with respect anova. Also, with the library moretest I had different Kolmovogov-Smirnov and A_D tests and pvalues. The differences are insignificant but I would like to know about it.

Thank you in advances and for the great program you have done!
Carmen
Attachments
Captura11.PNG
Captura11.PNG (10.48 KiB) Viewed 663 times
Captura12.PNG
Captura12.PNG (12.49 KiB) Viewed 663 times
User avatar
MAgojam
Posts: 421
Joined: Thu Jun 08, 2017 2:33 pm
Location: Parma (Italy)

Re: Differences in Shapiro-Wilk P.value with ANOVA

Post by MAgojam »

MOPOLV wrote: Mon Aug 14, 2023 7:11 am I have the same problem, I have obtained different shapiro-wilk pvalues in anova one-way and with respect anova ...
Hey Carmen,
a simple response on the fly.
The small differences you saw are due to the residuals passed through the shapiro-wilk test.
In anova one-way they are standardized residuals!
You can take a look at the source code here (#L56 and #L279):
https://github.com/jamovi/jmv/blob/mast ... vaonew.b.R

Cheers,
Maurizio Agosti
https://www.jamovi.org/about.html
Post Reply