I guess my first suggestion would be to “unbuild” the hierarchy and try to run the model with a single subject-worth of data and see where things stand at that point. I find debugging more complex models difficult and often find that simplifying helps. Have you tried that?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Hierarchical Binomial Model - Not converging | 2 | 906 | February 1, 2019 | |
| Parametrize mixed beta regression in non centered way | 6 | 1194 | April 17, 2018 | |
| Non-centered parameterization of a beta distribution? | 12 | 2837 | March 22, 2021 | |
| Convergence with noncentered hierarchical model | 6 | 840 | July 24, 2021 | |
| Non-centered parametrisation of bounded variables | 4 | 362 | January 31, 2024 |