This sounds to me like a CTHMM. @RJTK has done some work in this area (Multivariate time series inference). An alternative that PyMC3 handles well is a lagged regression (an example of which is also in that link)
chartl
2
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Time series example | 5 | 2839 | October 10, 2018 | |
| Hidden Markov Model - Predicting the next observation(s) of unseen sequences | 8 | 2169 | May 31, 2022 | |
| Time Series Forecasting in Pymc3 | 0 | 642 | July 22, 2021 | |
| Calculating conditional posterior predictive samples in high-dimensional observation spaces | 13 | 994 | July 7, 2023 | |
| Modeling stock market signals (online changepoint detection) | 3 | 1934 | March 29, 2020 |