Howdy, Stranger!

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

Supported by

How to deal with imbalance across 2 levels for Bayesian ANOVA

Hi

I am very new to Bayesian analysis and Jasp. I am trying to analyze data with 2 levels of conditions and finding the best possible way to do.

My data(RT,accuracy) involves 2 levels with 2 conditions(c1, c2) in level1 and 3 conditions(c3,c4,c5) in level2. c1 has all the three sub-conditions (c3,c4,c5) but c2 has only (c3,c4) for 3 different group of subjects. Since I cannot do repeated measures bayesian ANOVA due to this imbalance, may I know the optimal way to do the analysis

1) Should I just run multiple t-tests across all combinations for all the groups? If so, could you also point to a reference I can cite it?

2) Is it possible to do mixed measures in repeated measures bayesian ANOVA by considering all the conditions (13,14,15,23,24) under the same level and test across subjects?

It would be really helpful if the administrators could kindly suggest the best way to approach this problem.

Thank you
Alekhya

Comments

  • Dear Alekhya,

    Thanks for your question. This is tricky! Fundamentally, there is nothing holding you back from using the regular model and denoting the missing conditions as missing data. But what to do in your specific case? Basically, my advice is to spend some more sentences outlining the structure of your design (because I did not fully get it) and then ask for advice on the "Bayesian Inference in Psychology" Facebook group. Richard Morey might also have some sound advice.

    Cheers,
    E.J.

Sign In or Register to comment.