Jesse Grabowski

I have something ready to go on this, I would just need to clean it up a bit and re-focus it away from some of the tangential issues. Thoughts? https://github.com/jessegrabowski/VAR-Blog/blob/main/Big%20VAR%20Blog%20Post.ipynb

> But i'd love to see the argument made for why Bayesian VARs in particular are useful as per the example of a hierarchical case discussed in the post above....

Admittedly everythign in that last comment was not related to the issue. I'd be happy to write a smaller series, I'd also be happy to collaborate @NathanielF, if you're interested...

Yeah, I agree that using hierarchical prior to try to estimate VARs for many countries simultaneously is an open field of research. I've basically never seen a paper that does...

Yeah it's scheduled for depreciation per https://github.com/aesara-devs/aesara/pull/1188 I was a bit disappointed to see it go. The alternative is just to use loops like @ricardoV94 does in the PyMC Labs...

I made some comments on the notebook (which is great btw), but they are all very "fluffy". I'll try to have a look at the actual hierarchical implementation tonight. I...

I'm happy to put together notebook (2) entirely, building on your code/data from (1). Maybe we can fit the VAR on Ireland in part (1) and I can do the...

Looks like it's related to the changes to the `__len__` method in variables.py. I'd suggest just reverting the change unless we really need it. It's a pretty low-level thing that...

This was something on the Theano team's radar, I think at least one of the original devs was interested in piggy-backing on sympy for this purpose. See [this blog post](https://matthewrocklin.com/blog/work/2013/03/19/SymPy-Theano-part-1),...

Yes, I don't like adding a sympy dependency either. It's non-trivial to switch between representations (sympy and pytensor), mostly because of broadcasting stuff. From my own experience, it would be...