Jack Bailey

Of course, see below. ```r # Load packages library(tidyverse) library(labelled) library(readstata13) library(here) # Create data frame with labelled vectors dta % labelled( labels = c( "a" = 1, "b" =...

Thanks. I agree that supporting labelled vectors would be useful. While I could convert the labelled vectors to factors first, it's not useful in this case as it changes the...

I'd second that weighting would be useful. You've already taken a step into analysis in implementing the `chisq.test()` and `fisher.test()` functions. Why not allow for weighting too?

Possibly related to this issue https://github.com/paul-buerkner/brms/issues/1025

Not sure how you’re planning to implement this, but it might make sense to also rely on the ar() command that most often applies to auto-regressive variables.

@paul-buerkner, this is just an idle thought, but could you model the correlation matrix by assuming that it comes from an LKJ distribution (like we use as a prior anyway)...

I might be missing something, but in that case why not simply create a vector of correlation parameters the same length as the number of comparisons between response variables and...

Quick question: If I were to use @StaffanBetner's compression technique, could I compute the LOO scores correctly by passing the original data to add_criterion via prepare_predictions' newdata argument?

Thanks for looking into this Staffan. Another (maybe simpler) idea might simply be to have brms assert that any parameters modelled using a dirichlet prior are automatically considered to be...

Just flagging for anyone who's interested that @StaffanBetner has worked out a way to fit the model and shoehorn it into a brms object in the meantime https://discourse.mc-stan.org/t/dirichlet-prior-possible-with-stanvars/15812/5?u=jackbailey