Aki Vehtari

Any further thoughts on this? I'm fine adding `to_stan_json()` to any package, but we need a decision on where to put it

Was there resolution for this?

Bumping this reloo question up again

It seems there hasn't been much activity in rstantools, and some shared code is now in `posterior`. Given we have `posterior` it would be good to clarify what should go...

Is it helpful to have generics in `rstantools` in addition to having the actual computations like rhat in `posterior`

Tagging more authors @betanalpha, @danielcfurr, @hyunjimoon, @education-stan, @Cristinabarber, @joonho112, @LuZhangstat, @kaybenleroll, @milkha, @mbjoseph, @fonnesbeck

I just had a model for which optimizing failed as inits are far from sensible, but making the posterior closer to unit scale helps. I have these different length scale...

Could you use something else than `u` for variable, so that `u` is not on both left hand and right hand side? ``` u = l + (u - l)...

This > causes an error Error in prediction(x, ...) : unused argument (variable = "b_Intercept") is solved by ``` powerscale_sensitivity(fit_bin, prediction = \(x, ...) theta, variable='b_Intercept') ``` It would be...

The relevant PR in ggplot2 https://github.com/tidyverse/ggplot2/pull/5281