Interpretation RM ANOVA

GuillaumeC

Hi there,

I have some difficulty to interpret the result of this 2 time * 3 groups RM ANOVA, and any comments would be appreciate : )

I am particularly interesting by the interaction (Time x Group) ,

In line with the first attached image I can't conclude that there is strong evidence in favor of H0 compare to H1 (BF01 = .937), isn't it ?

However, how can interpret the BF01 of 1.951 when I put main effect "Time" and "Group" as nuisance ?

Thanks for your comments !

Guillaume

EJ

Hi Guillaume,

When you put "Time" and "Group" as nuisance, you are basically comparing the full model to the model with two main effects; that is, you are asking whether the inclusion of the interaction adds anything compared to the two main effects. You can get that same number from the original table by computing 0.937/0.483 = 1.94 (the small difference is due to the numerical error).

E.J.

GuillaumeC

Thanks EJ,

So, writing my paper it should be preferable to report the two informations (comparison of the full model against the two main effects only AND comparison of the full model against all candidate models) ?

Can I concluded something like "comparing to all candidate models, the data do not support evidence in favor of H0 (BF01 = 0.937) ; however comparing to the model with the two main effects the data indicated substantial evidence in favor of H0 (BF01 = 1.951), suggesting no clear effect of the experience on the dependent variable" (sorry if this sentence is horrible for a bayesian statistician )

Also, the data seems to support the effect of "group" - regarding to the present study, this result simply suggest that the randomization in each experimental groups do not create equal group regarding the dependent variable. It is puzzling here! How can I "control" this effect ? I mean, I would like to have the most precise indications to discuss the effect of my experience (i.e., group * time) on the dependent variable.

Thanks again fo your help,

Vive Jasp !

Guillaume

EJ

Hi Guillaume,
In Jeffreys's opinion, BFs in between 1/3 and 3 are "not worth more than a bare mention", and I agree. So that BF01 = 1.951 really doesn't tell us much. The effect of group is also not really compelling, so I would not lose sleep over it. Of course the fact that the evidence is inconclusive does not mean you haven't learned anything about the model parameters.
Cheers,
E.J.

GuillaumeC

Ok EJ,

Thanks for your comments