How to generate multiple posterior distributions under a single PyMC3 model based on multiple likelihoods and a constant prior
Let’s say I have a dataset consisting of two subsets with binary observations. Subsets have the same proportions but different lengths. Based on a fixed Beta prior and those two binomial likelihood distributions, I want to generate two posterior distributions of p. Then, I will collect the mean p’s in an estimation set. Instead of building two different models, I want to fulfill all inferences under a single model. Below you see the PyMC3 model: