Logcdf isn’t enough, icdf is also needed to avoid rejection sampling. According to this issue, that method is still missing for BetaBinomial: Add icdf functions for distributions · Issue #6612 · pymc-devs/pymc · GitHub
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Truncated normal distribution with optimal truncation thresholds via DensityDist | 8 | 3053 | June 21, 2018 | |
| Truncated Inverse normal distribution (also known as Wald distribution) | 15 | 2955 | April 27, 2018 | |
| Custom discrete distribution for zero truncated Poisson | 10 | 2608 | December 19, 2017 | |
| Hierarchical Binomial regression - ineffective sampling | 4 | 922 | January 17, 2018 | |
| Prior sample from TruncatedNormal gives inf | 3 | 544 | May 27, 2019 |