well, my main aim is trying to update the model based on new data, so, I wanted to do updating part which is kind of similar to Kalman filter. I saw one book but they concentrated on discrete without going to continuous part. So, I have few questions:
- how is it possible to implement Bayesian updating with pymc3?
- is there tutorial for creating custom distribution? I looked at pymc3 but still I am not sure I am doing it right.