Andrew Gelman

+1 > On Nov 15, 2019, at 12:45 PM, Lauren Kennedy wrote: > > @jgabry and I were talking that it might be handy to have extra functionality in bayesplot...

I agree. Indeed, for the purpose of testing ADVI, we _want_ examples that take awhile in NUTS, that’s part of the point. I’d say that, to be in the whitelist,...

I’m thinking of this in the context of advi-test. But the general principle remains: if an example is in the whitelist, it should _already_ have been succesfully fit using Nuts,...

Yes, within a half an order of magnitude is fine. > On Mar 3, 2016, at 12:21 PM, Bob Carpenter [email protected] wrote: > > If by "roughly", you mean to...

If we're gonna do one of these, I'd prefer the parentheses, as the braces look weird to me and the angle brackets make me thing of upper and lower. But...

Hi, you should include the Stan model, not the Bugs model! A > On Apr 9, 2016, at 6:19 PM, wdonald1985 [email protected] wrote: > > Here is the model. When...

Hi, thanks for sharing. I guess the function should be rewritten. I don't see an easy general solution because the x's could in theory all take on the same values,...

Hi, thanks for the kind words. Regarding the arsenic level: yes, I see your point. Something like the median and the 90th percentile, or the 25th and 75th percentile, would...

It would be great to have a couple fun examples of this (personally, I prefer 2-d plots to pseudo-3d) which we could write up as a notebook or even just...

Are you saying here that the variance parameter will vary by group? In which case maybe we want something like: stan_glm(formula1, formula2, …) so that it would look like stan_glm(y...