Gabriel Stechschulte

@tomicapretto ahh that makes sense. Thanks for the information and for fixing this in `formulae` and `bambi` already!

> Really cool! A few suggestions -- > > * `bayeux` could be invisible here, and you could access all the methods programatically. That's done [here](https://github.com/jax-ml/bayeux/blob/main/bayeux/_src/bayeux.py#L101), but i can factor...

In this example, the error is because bayeux is appending `_0` to `party_id_dim` of the posterior dims. This results in Bambi [discarding](https://github.com/GStechschulte/bambi/blob/9f1d9d179071abbb4cc6255242132829aae80faf/bambi/backend/pymc.py#L261C4-L261C86) all posterior dims because the dims in the...

> In this example, the error is because bayeux is appending `_0` to `party_id_dim` of the posterior dims. This results in Bambi [discarding](https://github.com/GStechschulte/bambi/blob/9f1d9d179071abbb4cc6255242132829aae80faf/bambi/backend/pymc.py#L261C4-L261C86) all posterior dims because the dims in...

@ColCarroll thanks for the information. @tomicapretto I can apply this post processing step on Bambi's side.

Two updates: 1. I added a processing step for when Bambi cleans the idata, it renames the idata dims and coordinates to match those of the underlying PyMC model. 2....

@ColCarroll thanks a lot for the review! I will incorporate these in the coming days.

Thanks for the reviews and suggestions @ColCarroll 😄 I have taken your suggestions and implemented them in slightly different ways. - Bambi has separate inference method calls for VI, MCMC,...

@tomicapretto should we allow optimization methods? I think it is really cool but `model.predict` will not work out of the box as optimization methods return `OptimizerResults` and not an idata...

> It would be cool if it could. It would allow non-Bayesians an entry point into Bayesian software/methods, with a simple change of sampler. > […](#) > On Mar 1,...