What would the right way to model a Multivariate Normal distribution be when on every observation some values are missing, ie., I have a very sparse input. Note that we
For example, my observations may look something like
[[1.11, --, 0.9, --, 1.23, --], [--, 1.2, 0.81, --, --, --], [--, --, --, --, 1.21, --], ... ]
I was initially letting PyMC handle it, but I realise now that that isn’t the right way because the samples are drawn iid.
It has been mentioned in a few places on the forums that
pm.Potential can be used in such cases but what exactly is a potential in this context and how might I use it here?