5. Visualising MCMC results

The best way to visualise and check the results when using sampling is to use the ArviZ library. This library is designed to work with a range of sampling packages, including NumPyro. It provides a range of functions for visualising the results of sampling, including trace plots, density plots, and posterior predictive checks.

I won’t go into detail about how to use ArviZ here, as the ArviZ documentation is very good and covers everything you could need.