Add ordinal probit and logit models to BoomSpikeSlab

[steve-the-bayesian]

C++ work is mostly done. Just need the glue. They can even use the same posterior sampler.

[hrlai]

Dear @steve-the-bayesian , thank you so much for the bsts package. Very stoked to see it offering options for non-Gaussian responses. I'm dealing with ordinal categorical responses, is it one of the planned feature for bsts in the near future? I presume many will be dealing with ordinal data, e.g., from surveys as well.

Thanks :)

[steve-the-bayesian]

It's on the wish list, but not high enough to make it on the short term road map. Glad you're enjoying the package!

On Tue, May 2, 2023 at 2:30 PM Hao Ran Lai @.***> wrote:

Dear @steve-the-bayesian https://github.com/steve-the-bayesian , thank you so much for the bsts package. Very stoked to see it offering options for non-Gaussian responses. I'm dealing with ordinal categorical responses, is it one of the planned feature for bsts in the near future? I presume many will be dealing with ordinal data, e.g., from surveys as well.

Thanks :)

— Reply to this email directly, view it on GitHub https://github.com/steve-the-bayesian/BOOM/issues/31#issuecomment-1532179309, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABMVDVK3JKBS5R25QUT337LXEF4G3ANCNFSM4HMENOFA . You are receiving this because you were mentioned.Message ID: @.***>

[hrlai]

Thanks for the update. I'll keep exploring this and other paths while waiting for this to come out :)