Jonah Gabry

Hi @janupra99, thanks, but is there a reason for this change? It looks like it just changes `stan-dev` to `Stan-dev`, but the name of the github organization is `stan-dev` (all...

I think it's useful to have the centered parameterization too, as a comparison. So maybe we could have the one called "eight_schools" be the better parameterization (in this case non-centered)...

On Friday, July 15, 2016, Michael Betancourt [email protected] wrote: > We desperately need to avoid names like “good” and “bad”, or > “right” and “wrong”, as the correct parameterization depends...

Maybe three different eight schools models: the first with the actual data (NCP better), the second with y scaled up by 10 but sigma the same (CP is better), and...

> Have you thought about this? Not much but seems like a good thing to think about > I currently represent draws as a named object of numeric arrays. Think...

I'll think a bit more about this too, but in the meantime @jsocolar do you want to add a note about RAM in the doc? Regardless of whether we go...

@mjskay yeah I'd like to see more standardization in the interfaces too. the rstantools package (which includes lots of generics) was an initial attempt to get some of unification of...

@paul-buerkner I added `posterior_interval` and `predictive_interval` to the list above

Also, where it says > a little wrangling with Jensen’s inequality shows that the expectation of the log is less than or equal to the log of the expectation this...

> I think it's mentioned in the vignette but probably not elsewhere. I forgot about the vignette. You're right, it does show this behavior there. I can also add something...