In general you shouldn’t ignore those warnings, as they indicate that something in the geometry of your problem makes it hard for MCMC to explore: so, you can’t tell how the unexplored regions may affect your results. You’ll find answers to your questions and suggestions on how to remove these warnings in Divergent transitions - a primer.
mcol
2
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Handeling divergent warnings | 3 | 564 | August 16, 2022 | |
| Is it safe to ignore max_treedepth warnings if other diagnostics (ESS, Rhat, loo) are acceptable? | 3 | 1085 | August 23, 2021 | |
| Divergent transitions and exceed max treedepth warning | 5 | 4342 | August 17, 2020 | |
| Automagically increase `adapt_delta` until all divergences are eliminated, what could go wrong? | 17 | 1296 | June 28, 2021 | |
| Adapt_delta and chain length | 22 | 5286 | September 11, 2017 |