Aki Vehtari

@paul-buerkner reports for brms paul-buerkner/brms#873 > With the ovarian cancer data, inference is about 15% faster on average with the C.1 parameterization on my machine and shows similar convergence in...

I've been running ovarian and related prostate with 10 chains

I think the following should work, but fails due to constant y error ``` d_bin

Use posterior also for Rhat, ESS and MCSE. Currently ShinyStan is using old Rhat code (copy pasted from RStan in 2015).

The reference is https://arxiv.org/abs/1507.02646 Thanks for reminding about this issue. In addition to the reference we need to write a bit more documentation.

With algorithm='optimizing' Stan first finds maximum a posteriori solution using L-BFGS algorithm. Approximate posterior draws are obtained sampling from a normal distribution centered at the mode and covariance set based...

The example has moved to https://avehtari.github.io/ROS-Examples/Scalability/scalability.html (I also edited my comment above to have the new link)

Why only a Gaussian outcome? Why not all observation models with scale parameters?

To prepare for the future, it's good to also think that there might be more output distribution families with other parameters than sigma. For example, people making survival analysis would...

ggdensity extension to ggplot seems great for plotting 2D HPD regions https://jamesotto852.github.io/ggdensity/