RM-ANOVA Post-Hoc T-Test SE is Wrong, no longer pooled

Discuss statistics related things
Post Reply
emcourt33
Posts: 1
Joined: Tue Oct 19, 2021 8:19 am

RM-ANOVA Post-Hoc T-Test SE is Wrong, no longer pooled

Post by emcourt33 »

The post-hoc pair-waise comparisons following a repeated measures ANOVA used to use pooled variance and have a consistent SE in each t-test comparison. Now, Jamovi seems to use different SE for each t-test. Is this due to a change in the emmeans function or am I simply doing something wrong?
Attachments
Screen Shot 2021-10-18 at 11.51.05 PM.png
Screen Shot 2021-10-18 at 11.51.05 PM.png (144.2 KiB) Viewed 5066 times
User avatar
Ravi
Posts: 194
Joined: Sat Jan 28, 2017 11:18 am

Re: RM-ANOVA Post-Hoc T-Test SE is Wrong, no longer pooled

Post by Ravi »

Hi,
Earlier this year we changed the way we calculate the estimated marginal means (on which the post-hoc tests are based) as per recommendation of the author of the package we use to estimate the RM ANOVA: https://cran.r-project.org/web/packages/afex/vignettes/afex_anova_example.html. It now uses a multivariate model in its calculations: https://github.com/jamovi/jmv/commit/a9c8cb0

Cheers,
Ravi
Post Reply