Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Supported by

interactions Inclusion BF for matched models

Hi,

It is my understanding that when setting in the Effects output "Across matched model", inclusion BFs are computed for each effect without models that include higher-order interactions with that effect.

If so, it is unclear why the inclusion BF changes for the interaction between "Across all models" and "Across matched model" as there are no models with a higher order interaction:

Across all models:

Across matched models

Note also that the probabilities of the inclusion are unchanged, which again would suggest that the change is somehow in the probability of exclusion - but again, there are no models with higher order interactions to not include in the excluded models (that's a mouth full!)


Thanks!

Comments

  • Looking at the code, I understand that models with interactions are compared only to models with all the main effects. But why is this?

  • Okay, never mind - I got it now - reading the original post more closely ^_^

  • Happy to hear the problem solved itself! In case anything is still unclear feel free to ask.

Sign In or Register to comment.