Carlos Parada

> LOO-CV can be viewed as a proxy for Bayesian evidence / marginal likelihood. Clarification in case someone stumbles across this in the future: This isn't _quite_ true. Bayesian evidence...

> Yes, this is a hack. I've tried with a Bernoulli, but somehow I could not because of name clashes with `Distributions`, `DistributionsAD` and `Turing`, which all are re-exported in...

> The `*Like` is a viable way. I tried using the type itself and had a nasty bug Hmm, what happened? Maybe @devmotion will have some idea (since he's more...

> > Yes, this is a hack. I've tried with a Bernoulli, but somehow I could not because of name clashes with `Distributions`, `DistributionsAD` and `Turing`, which all are re-exported...

> Is a new struct needed? Could you just use `Distributions.Bernoulli`? Or the link functions in GLM? I would expect you could use `Distributions.Bernoulli` by passing the type itself, but...

You might want to take a look at the fit function in Dists.jl: https://github.com/JuliaStats/Distributions.jl/blob/71f1b1e39ad2b66b4865b5e1fd537315c8a53ae8/src/genericfit.jl#L8-L15 Which works with distribution types directly.

It should also be more generalizable — it would be super useful if you could pass an arbitrary likelihood from Dists.jl.

@storopoli does TuringGLM currently work by writing out the most common GLMs one at a time? In theory, you should be able to work with any likelihood, including ones specified...

> The likelihood API would need a rewrite. I haven't touched anything `InvLink` related. Sorry, can you clarify what you mean by this?

> It's easiest for me to do this as 1.7 and later. Trying to make it work in 1.6 and earlier, is substantial work that I am also not sure...