Gavin Simpson

Hi @FriedaBella. It's perfectly fine to ask questions or make feature requests here. I'm not familiar with Andres' **betapart** work; are you asking to have Bray-Curtis and Sorensen distances implemented...

This needs work outside of gratia, likely in a tidybayes.gam package

Thanks for the report @StefanoMezzini! The error comes from `parametric_effects()` in this line: ```r data

Fixing this should involve the standard non-standard evaluation ideas of modifying the original call (stored in `m$call`) to be a call to `model.frame()` instead of `bam()`, replacing the used formula...

@UniversidadNacionalAsuncion You know this is a **read only** mirror of the R sources? Nothing is going to happen with this PR. You should file a bug on R's bug tracker...

> The author name is shown as "¿citation_author?" in the pdf on the gratia github. Not sure if this is normal. This seems to be OK in version generated by...

> Going back to the boring situation in which we "read the documentation", in ?smooth.construct we have: >> null.space.dim: The dimension of the penalty null space (before centering). So I...

Some further reading has helped, if we're just talking about the Null space of a penalty. The key point I think is that the null space is the span of...

Here's some clearer evidence that the smooths have a null space. This needs the very latest version of gratia from github but equivalent results can be achieved with `mgcv::smoothCon(..., diagonal.penalty...

@dill > The formulation for the GAM (first display equation) doesn't allow for multivariate smooths. Fixed; Dave and I spoke about this while at ISEC this summer and we couldn't...