Levene's test of homogeneity of variances in ANCOVA

Discuss the jamovi platform, possible improvements, etc.

by thecuriouslamp » Tue Feb 25, 2020 10:13 am

Hello,

I was doing a univariate ANCOVA with the pre-test results as the covariate and the post-test results as the DV.
I ran the Levene's test of homogeneity of variance and somehow to my surprise, the test did not take the covariate into account - the results were just identical to running an ANOVA with no covariates specified in the model.

Has anyone else figured out similar problems and would the development team consider solving this in the next release?

Thank you very much!
thecuriouslamp
 
Posts: 2
Joined: Tue Feb 25, 2020 8:44 am

by jonathon » Tue Feb 25, 2020 10:24 am

hi,

can you attach a .omv file demonstrating this?

with thanks
User avatar
jonathon
 
Posts: 1689
Joined: Fri Jan 27, 2017 10:04 am

by jonathon » Tue Feb 25, 2020 11:28 am

it's ok, i've taken a look, we'll push out a fix in the next release.

thanks for reporting.

jonathon
User avatar
jonathon
 
Posts: 1689
Joined: Fri Jan 27, 2017 10:04 am

by thecuriouslamp » Tue Feb 25, 2020 12:56 pm

Thank you very much!
thecuriouslamp
 
Posts: 2
Joined: Tue Feb 25, 2020 8:44 am

by ard » Fri Feb 26, 2021 4:53 pm

I had a similar issue when running my ANCOVA where an error message appeared saying that they could not find my pre-test variable. Is that part of a bug that will be fixed in the next release? (Also, how often are there releases just to manage my expectations).
ard
 
Posts: 1
Joined: Wed Feb 24, 2021 4:30 pm

by jonathon » Fri Feb 26, 2021 11:06 pm

hi,

you may notice this thread is over a year old. can you start a new thread?

with thanks
User avatar
jonathon
 
Posts: 1689
Joined: Fri Jan 27, 2017 10:04 am


Return to General