Prior predictive checking: especially seasonal burden #251
Labels
enhancement
New feature or request
experiment
some sort of experiment to better understand a part of the model
I was wondering if there was any prior predictive checking for the covid model(s)?
@tjhladish and I were talking about bringing the seasonal burden into the posterior distribution, which would effectively penalise extremely a priori unlikely outcomes. However, before assessing that it would be good to understand what the model parameter priors currently imply about likely/unlikely a priori outcomes.
Good reference: this classic https://arxiv.org/abs/2011.01808
The text was updated successfully, but these errors were encountered: