This is explicitly not allowed. If you want to do it you have to implement your own step sampler that just returns draws from the prior. To my knowledge there is about 0 work out there suggesting you would ever want to do this.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| DensityDist conditional random() method | 7 | 1093 | July 5, 2019 | |
| Can pm.draw() be used inside a pymc model or will it break links between RVs and observed/likelihood variable? | 5 | 577 | May 8, 2023 | |
| Call MvNormal.random() method inside model | 3 | 1159 | August 29, 2018 | |
| Stochastic node from a trace - or sharing params across models | 2 | 472 | December 8, 2020 | |
| Unobserved variables in blackbox likelihood | 11 | 1121 | October 14, 2019 |