Advanced contrasts options

Discuss the jamovi platform, possible improvements, etc.

by pandelis » Thu Dec 12, 2019 9:52 am

Hi,

Do you know if the implementation of avanced contrasts options still planned or not? (this is still for me the missing feature to teach my ANOVA lectures with Jamovi).
https://github.com/jamovi/jamovi/issues/342

Best regards
Last edited by pandelis on Thu Dec 12, 2019 10:12 am, edited 1 time in total.
pandelis
 
Posts: 5
Joined: Thu Sep 28, 2017 7:16 am

by jonathon » Thu Dec 12, 2019 9:56 am

hi,

yeah, i'm really sorry, it's probably not going to happen in the near future.

we'd love to do it, but ... well, so much to do, and so little time.

sorry i don't have better news.

jonathon
User avatar
jonathon
 
Posts: 1049
Joined: Fri Jan 27, 2017 10:04 am

by pandelis » Thu Dec 12, 2019 10:18 am

Thank you for your quick answer !

Aaah it's so sad... (but it's nice to know)
I also tried to implement classic ANOVA contrasts in regression (with one column for one contrast) but this seems not to work all the time...
pandelis
 
Posts: 5
Joined: Thu Sep 28, 2017 7:16 am

by jonathon » Thu Dec 12, 2019 10:19 am

oh, that should work ... if you don't think it's working the way it should, then do make a bug report.

with thanks
User avatar
jonathon
 
Posts: 1049
Joined: Fri Jan 27, 2017 10:04 am

by Ravi » Fri Dec 13, 2019 7:38 am

This was probably due to the default contrast being a simple contrast (fixing the intercept to the grand mean). However, in the latest version we let it default to a dummy contrast (fixing the intercept to the reference level) which is also the default in R and SPSS. So give it another try with the latest version.
User avatar
Ravi
 
Posts: 143
Joined: Sat Jan 28, 2017 11:18 am


Return to General