Effective Sample Size for Random Effects?

Hi,

Is there a way to see the effective sample size - Eff.Sample - for the random effects in brms()?

Many thanks,

rhat(model)
2 Likes

Hi,

I am confused now.
I thought rhat returns the

potential scale reduction factor on split chains.

and tells me if there is a difference between within and between chain variances/means?
What is the function neff_ratio then for?

There are multiple ways to assess convergence. One is rhat and another is the effective sample size (or the effective sample size divided by the total number of samples). You may also take a look at the more general intro of our paper https://arxiv.org/abs/1903.08008