Another Bayesian model of coronavirus progression

Jon Zelner writes:

Just ran across this paper [Estimating unobserved SARS-CoV-2 infections in the United States, by T. Alex Perkins, Sean Cavany, Sean Moore, Rachel Oidtman, Anita Lerch, and Marya Poterek] which I think is worth signal-boosting.

I [Jon] also think that the model in here could potentially be implemented in Stan (though it might require some work on marginalizing the branching process model) and could be quite useful if it could be made more hierarchical.

The point here is not that these particular estimates are correct—as always, inferences are only as good as the data they’re based on—but that the model in this paper could be useful more generally.

See here, here, here, and here for further discussion of coronavirus models.