Sign in with your CogSci, Facebook, Google, or Twitter account.

Or register to create a new account.

We'll use your information only for signing in to this forum.

Supported by

Bayes Loglinear Analysis


I see that Bayesian loglinear analysis is implemented in JASP. I was wondering whether there is documentation/publications for this. My understanding is that JASP is running the R scripts for BayesFactor in the background, so if there's documentation for the BayesFactor package I'd happily take that (actually I'd probably prefer it). If it is implemented in BayesFactor, is there a help file for the relevant script?

If there is no documentation, are there publications you might direct me towards? I've seen Bayesian loglinear analyses implemented in other packages, but I think the discrepancy measures are different to what JASP is doing.

Thanks in advance!



  • edit I think the JASP implementation of loglinear analysis is based on Overstall and King's 'conting' [R] package. Is that correct? Are the BFs then based on the posterior model probabilities?

  • EJEJ Posts: 461

    Yes, it is based on conting! It uses Reversible Jump MCMC, and under uniform prior probabilities for the models, the number of visits relates directly to the posterior probabilities (and this also given the BF).

  • That's great, thanks so much EJ!

Sign In or Register to comment.