Sourish

Do you want to add it to Turing? And then just call it in `SurvivalAnalysis.jl`? Or do you want to develop it as part of `SurvivalAnalysis.jl` with `Turing.jl`?

My only concern is that if we build too many packages, each package's maintenance could be a headache. So `SurvivalBayesian.jl` could be part of your `SurvivalAnalysis.jl`. Of course, it will...

Wonderful. Looking forward to our discussion tomorrow.

- Adding this discussion on discourse [here](https://discourse.julialang.org/t/survival-analysis-in-turing-vectorized-version-leads-to-strange-errors/86301). - The paper on `rstanrm` package for Bayesian Survival Analysis in `R` is [here](https://arxiv.org/pdf/2002.09633.pdf).

I also need multinomial logistic regression with the lasso. Do you have a developer document? I want to develop. Please let me know if it is possible !

In `smoothcv`, the arguement `λ` - is it scalar? or is it vector? From your code, I think it is scalar. However, in the following line `λ` is trated as...

> > In `smoothcv`, the arguement `λ` - is it scalar? or is it vector? From your code, I think it is scalar. However, in the following line `λ` is...

> Hi both and thanks! Let me just mention the following: All of the above timings are quite slow because you use leave-one-out cross-validation (LOO-CV). If instead, you used e.g.,...

> > The purpose of "Bayesian Optimisation" is to speed up the optimisation when your objective function is insanely expensive, such as LOO-CV. > > Agreed. My point above was...

If you choose `nu=0` the marginal prior distribution for location parameter for the Normal Gamma model would be Cauchy distribution. This is a proper distribution for which mean and variance...