Alejandro Catalina

In many cases approximate LOO is already a good estimate, and in that case we don't really care about number of datapoints as the matrix multiplication is reasonably fast, and...

There is already a prototype working in `workflow` branch. If anyone is interested I can give some instructions. Basically, using `varsel_cv` in `workflow` branch as in `cv_varsel` in `develop` branch...

It is not easy to fix unfortunately. We will add documentation. Get Outlook for iOS ________________________________ From: Frank Weber ***@***.***> Sent: Thursday, August 12, 2021 11:32:18 AM To: stan-dev/projpred ***@***.***>...

When discussing this, we got to the conclusion that we would not allow projections without intercept. Therefore, I'm removing this argument altogether, as we don't think it makes sense to...

The reason we didn't dedicate time to models without intercepts is that in general that's not a good practice, just commenting for reference. However, now that the PR is up...

Yes, that’s our reasoning. From: Frank Weber ***@***.***> Date: Friday, 21. January 2022 at 12.07 To: stan-dev/projpred ***@***.***> Cc: Alejandro Catalina ***@***.***>, Comment ***@***.***> Subject: Re: [stan-dev/projpred] Omitting intercept in...

Yes I do agree but, as you mention, there is no harm in including the intercept in those cases, so it should be fine. Get Outlook for iOS ________________________________ From:...

Yeah, that for sure, there would be a bit of correlation, but should be minor. We cam include an option for these cases but then again, should be uncommon case....

So the idea of this argument is to avoid computational cost by not refitting the projections with `ndraws_pred` precisely. We can add your suggestion for `project` only. By the way,...

I guess the problem is rather in split formula as we don’t recognize these terms currently. Best, Alex ________________________________ From: Frank Weber ***@***.***> Sent: Monday, August 2, 2021 11:05:10 AM...