models.mcmc_diagnostics()

MCMC diagnostics of chains of draws (Vehtari et al. 2021, as R’s

Usage

models.mcmc_diagnostics(chains)

posterior): rank-normalized split R-hat, bulk and tail effective sample sizes, the effective sample size of the mean and its Monte Carlo standard error.

Parameters

chains: list of list of float

Equal-length chains, at least 4 draws each.

Returns

dict

rhat, ess_bulk, ess_tail, ess_mean, mcse_mean.

Examples

>>> from prospicio.models import mcmc_diagnostics
>>> a = [float((i * 37) % 101) for i in range(400)]
>>> b = [float((i * 53 + 7) % 101) for i in range(400)]
>>> mcmc_diagnostics([a, b])["rhat"] < 1.01

True