Predict with a phylogenetic model for a new species with known phylogenetic position

[loubar]

Would it be possible to implement a way of predicting from a phylogenetic model for a new species when it’s phylogenetic position is known? When sampling new levels, I would like to use the species' position in cov_ranef.

[paul-buerkner]

Thanks for opening this issue.

Refers to discussion https://discourse.mc-stan.org/t/predict-with-a-brms-phylogenetic-model-for-a-new-species-with-known-phylogenetic-position/7480/

[jonnations]

I know you're super busy, but any development on this? I tried the newdata2 argument in predict(). I mentioned that on discourse here. The prediction ran, but it didn't seem to include the new covariance matrix in the predictions. Any suggestions on where to look to predict newdata that includes the use of a covariance matrix in Stan? Thanks :)

[paul-buerkner]

This is not yet implemented. Sorry.

[lyinch]

Hello,

Is there any progress on this, or any way someone could help?

Thanks

[paul-buerkner]

Implementing this is non-trivial and I don't have much time to work on complicated brms features these days. Eventually, it will have to be implemented in get_new_rdraws which you can find in https://github.com/paul-buerkner/brms/blob/master/R/prepare_predictions.R